ScanNet200 3D Semantic Label Benchmark
The 3D semantic labeling task involves predicting a semantic labeling of a 3D scan mesh.
Evaluation and metricsOur evaluation ranks all methods according to the PASCAL VOC intersection-over-union metric (IoU). IoU = TP/(TP+FP+FN), where TP, FP, and FN are the numbers of true positive, false positive, and false negative pixels, respectively. Predicted labels are evaluated per-vertex over the respective 3D scan mesh; for 3D approaches that operate on other representations like grids or points, the predicted labels should be mapped onto the mesh vertices (e.g., one such example for grid to mesh vertices is provided in the evaluation helpers).
This table lists the benchmark results for the ScanNet200 3D semantic label scenario.
Method | Info | avg iou | head iou | common iou | tail iou | alarm clock | armchair | backpack | bag | ball | bar | basket | bathroom cabinet | bathroom counter | bathroom stall | bathroom stall door | bathroom vanity | bathtub | bed | bench | bicycle | bin | blackboard | blanket | blinds | board | book | bookshelf | bottle | bowl | box | broom | bucket | bulletin board | cabinet | calendar | candle | cart | case of water bottles | cd case | ceiling | ceiling light | chair | clock | closet | closet door | closet rod | closet wall | clothes | clothes dryer | coat rack | coffee kettle | coffee maker | coffee table | column | computer tower | container | copier | couch | counter | crate | cup | curtain | cushion | decoration | desk | dining table | dish rack | dishwasher | divider | door | doorframe | dresser | dumbbell | dustpan | end table | fan | file cabinet | fire alarm | fire extinguisher | fireplace | floor | folded chair | furniture | guitar | guitar case | hair dryer | handicap bar | hat | headphones | ironing board | jacket | keyboard | keyboard piano | kitchen cabinet | kitchen counter | ladder | lamp | laptop | laundry basket | laundry detergent | laundry hamper | ledge | light | light switch | luggage | machine | mailbox | mat | mattress | microwave | mini fridge | mirror | monitor | mouse | music stand | nightstand | object | office chair | ottoman | oven | paper | paper bag | paper cutter | paper towel dispenser | paper towel roll | person | piano | picture | pillar | pillow | pipe | plant | plate | plunger | poster | potted plant | power outlet | power strip | printer | projector | projector screen | purse | rack | radiator | rail | range hood | recycling bin | refrigerator | scale | seat | shelf | shoe | shower | shower curtain | shower curtain rod | shower door | shower floor | shower head | shower wall | sign | sink | soap dish | soap dispenser | sofa chair | speaker | stair rail | stairs | stand | stool | storage bin | storage container | storage organizer | stove | structure | stuffed animal | suitcase | table | telephone | tissue box | toaster | toaster oven | toilet | toilet paper | toilet paper dispenser | toilet paper holder | toilet seat cover dispenser | towel | trash bin | trash can | tray | tube | tv | tv stand | vacuum cleaner | vent | wall | wardrobe | washing machine | water bottle | water cooler | water pitcher | whiteboard | window | windowsill |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ||
IMFSegNet | 0.334 9 | 0.532 13 | 0.251 11 | 0.179 7 | 0.486 9 | 0.041 16 | 0.139 13 | 0.003 1 | 0.283 4 | 0.000 1 | 0.274 15 | 0.191 15 | 0.457 14 | 0.704 14 | 0.795 7 | 0.197 9 | 0.830 6 | 0.000 3 | 0.710 9 | 0.055 16 | 0.064 4 | 0.518 6 | 0.305 10 | 0.458 17 | 0.216 12 | 0.027 5 | 0.284 13 | 0.000 1 | 0.000 3 | 0.044 12 | 0.406 10 | 0.561 7 | 0.000 1 | 0.080 12 | 0.000 3 | 0.873 9 | 0.021 15 | 0.683 8 | 0.000 7 | 0.076 9 | 0.494 10 | 0.363 9 | 0.648 16 | 0.000 1 | 0.000 2 | 0.425 9 | 0.649 4 | 0.000 10 | 0.668 12 | 0.908 7 | 0.740 11 | 0.010 14 | 0.206 8 | 0.862 10 | 0.000 1 | 0.000 11 | 0.560 9 | 0.000 7 | 0.359 13 | 0.237 11 | 0.631 12 | 0.408 11 | 0.411 4 | 0.322 15 | 0.246 4 | 0.439 10 | 0.599 13 | 0.047 4 | 0.213 7 | 0.940 10 | 0.139 11 | 0.000 1 | 0.369 5 | 0.124 10 | 0.188 12 | 0.495 11 | 0.624 11 | 0.626 8 | 0.320 14 | 0.595 4 | 0.495 8 | 0.496 10 | 0.000 4 | 0.000 1 | 0.340 12 | 0.014 6 | 0.032 7 | 0.135 5 | 0.000 4 | 0.903 8 | 0.277 6 | 0.612 8 | 0.196 7 | 0.344 12 | 0.848 13 | 0.260 6 | 0.000 1 | 0.574 13 | 0.073 16 | 0.062 4 | 0.000 4 | 0.000 1 | 0.091 6 | 0.839 3 | 0.776 3 | 0.123 12 | 0.392 9 | 0.756 12 | 0.274 5 | 0.518 12 | 0.029 16 | 0.842 4 | 0.000 6 | 0.357 13 | 0.000 1 | 0.035 7 | 0.000 3 | 0.444 12 | 0.793 2 | 0.245 5 | 0.000 1 | 0.512 16 | 0.512 15 | 0.159 15 | 0.713 13 | 0.000 10 | 0.000 1 | 0.336 13 | 0.484 12 | 0.569 2 | 0.852 9 | 0.615 6 | 0.120 12 | 0.068 10 | 0.228 8 | 0.000 1 | 0.733 10 | 0.773 2 | 0.190 4 | 0.000 10 | 0.608 6 | 0.792 4 | 0.000 1 | 0.597 7 | 0.000 14 | 0.025 2 | 0.000 1 | 0.573 17 | 0.000 2 | 0.000 1 | 0.508 11 | 0.555 8 | 0.363 10 | 0.139 12 | 0.610 2 | 0.947 8 | 0.305 7 | 0.594 9 | 0.527 9 | 0.009 17 | 0.633 13 | 0.000 1 | 0.060 3 | 0.820 5 | 0.604 15 | 0.799 9 | 0.000 1 | 0.799 11 | 0.034 14 | 0.784 13 | 0.000 1 | 0.618 6 | 0.424 2 | 0.134 16 | 0.646 13 | 0.214 14 | |||||||||||||||||||||||||||||
OA-CNN-L_ScanNet200 | 0.333 11 | 0.558 5 | 0.269 9 | 0.124 13 | 0.448 14 | 0.080 9 | 0.272 5 | 0.000 3 | 0.000 7 | 0.000 1 | 0.342 8 | 0.515 4 | 0.524 7 | 0.713 13 | 0.789 9 | 0.158 12 | 0.384 12 | 0.000 3 | 0.806 6 | 0.125 7 | 0.000 9 | 0.496 8 | 0.332 7 | 0.498 14 | 0.227 8 | 0.024 6 | 0.474 3 | 0.000 1 | 0.003 2 | 0.071 9 | 0.487 3 | 0.000 11 | 0.000 1 | 0.110 8 | 0.000 3 | 0.876 7 | 0.013 17 | 0.703 3 | 0.000 7 | 0.076 9 | 0.473 12 | 0.355 11 | 0.906 6 | 0.000 1 | 0.000 2 | 0.476 6 | 0.706 1 | 0.000 10 | 0.672 10 | 0.835 13 | 0.748 9 | 0.015 13 | 0.223 7 | 0.860 11 | 0.000 1 | 0.000 11 | 0.572 7 | 0.000 7 | 0.509 7 | 0.313 7 | 0.662 4 | 0.398 13 | 0.396 8 | 0.411 13 | 0.276 2 | 0.527 4 | 0.711 5 | 0.000 7 | 0.076 13 | 0.946 6 | 0.166 6 | 0.000 1 | 0.022 10 | 0.160 7 | 0.183 13 | 0.493 13 | 0.699 9 | 0.637 6 | 0.403 6 | 0.330 12 | 0.406 13 | 0.526 6 | 0.024 2 | 0.000 1 | 0.392 11 | 0.000 11 | 0.016 16 | 0.000 12 | 0.196 3 | 0.915 5 | 0.112 12 | 0.557 10 | 0.197 6 | 0.352 10 | 0.877 3 | 0.000 12 | 0.000 1 | 0.592 12 | 0.103 11 | 0.000 14 | 0.067 1 | 0.000 1 | 0.089 7 | 0.735 7 | 0.625 11 | 0.130 9 | 0.568 6 | 0.836 7 | 0.271 8 | 0.534 9 | 0.043 13 | 0.799 11 | 0.001 5 | 0.445 5 | 0.000 1 | 0.000 8 | 0.024 2 | 0.661 4 | 0.000 5 | 0.262 3 | 0.000 1 | 0.591 8 | 0.517 13 | 0.373 8 | 0.788 7 | 0.021 8 | 0.000 1 | 0.455 4 | 0.517 9 | 0.320 8 | 0.823 12 | 0.200 16 | 0.001 17 | 0.150 5 | 0.100 12 | 0.000 1 | 0.736 9 | 0.668 10 | 0.103 14 | 0.052 6 | 0.662 4 | 0.720 8 | 0.000 1 | 0.602 6 | 0.112 7 | 0.002 6 | 0.000 1 | 0.637 9 | 0.000 2 | 0.000 1 | 0.621 10 | 0.569 5 | 0.398 9 | 0.412 5 | 0.234 12 | 0.949 6 | 0.363 5 | 0.492 14 | 0.495 11 | 0.251 4 | 0.665 9 | 0.000 1 | 0.001 11 | 0.805 7 | 0.833 6 | 0.794 11 | 0.000 1 | 0.821 5 | 0.314 5 | 0.843 11 | 0.000 1 | 0.560 10 | 0.245 7 | 0.262 6 | 0.713 4 | 0.370 11 | |||||||||||||||||||||||||||||
CSC-Pretrain | ![]() | 0.249 17 | 0.455 17 | 0.171 16 | 0.079 17 | 0.418 15 | 0.059 14 | 0.186 10 | 0.000 3 | 0.000 7 | 0.000 1 | 0.335 10 | 0.250 13 | 0.316 16 | 0.766 7 | 0.697 17 | 0.142 13 | 0.170 14 | 0.003 2 | 0.553 14 | 0.112 9 | 0.097 1 | 0.201 16 | 0.186 14 | 0.476 15 | 0.081 16 | 0.000 9 | 0.216 17 | 0.000 1 | 0.000 3 | 0.001 17 | 0.314 17 | 0.000 11 | 0.000 1 | 0.055 15 | 0.000 3 | 0.832 16 | 0.094 3 | 0.659 15 | 0.002 5 | 0.076 9 | 0.310 16 | 0.293 17 | 0.664 14 | 0.000 1 | 0.000 2 | 0.175 17 | 0.634 6 | 0.130 2 | 0.552 17 | 0.686 17 | 0.700 17 | 0.076 7 | 0.110 15 | 0.770 17 | 0.000 1 | 0.000 11 | 0.430 17 | 0.000 7 | 0.319 15 | 0.166 15 | 0.542 17 | 0.327 16 | 0.205 16 | 0.332 14 | 0.052 16 | 0.375 13 | 0.444 17 | 0.000 7 | 0.012 17 | 0.930 17 | 0.203 3 | 0.000 1 | 0.000 12 | 0.046 12 | 0.175 14 | 0.413 16 | 0.592 14 | 0.471 16 | 0.299 15 | 0.152 16 | 0.340 16 | 0.247 17 | 0.000 4 | 0.000 1 | 0.225 15 | 0.058 3 | 0.037 4 | 0.000 12 | 0.207 2 | 0.862 15 | 0.014 14 | 0.548 13 | 0.033 16 | 0.233 16 | 0.816 16 | 0.000 12 | 0.000 1 | 0.542 15 | 0.123 5 | 0.121 1 | 0.019 2 | 0.000 1 | 0.000 11 | 0.463 16 | 0.454 17 | 0.045 17 | 0.128 17 | 0.557 15 | 0.235 14 | 0.441 16 | 0.063 11 | 0.484 17 | 0.000 6 | 0.308 17 | 0.000 1 | 0.000 8 | 0.000 3 | 0.318 17 | 0.000 5 | 0.000 9 | 0.000 1 | 0.545 14 | 0.543 12 | 0.164 14 | 0.734 9 | 0.000 10 | 0.000 1 | 0.215 17 | 0.371 16 | 0.198 14 | 0.743 14 | 0.205 15 | 0.062 15 | 0.000 11 | 0.079 14 | 0.000 1 | 0.683 16 | 0.547 16 | 0.142 9 | 0.000 10 | 0.441 11 | 0.579 15 | 0.000 1 | 0.464 14 | 0.098 9 | 0.041 1 | 0.000 1 | 0.590 14 | 0.000 2 | 0.000 1 | 0.373 13 | 0.494 14 | 0.174 15 | 0.105 16 | 0.001 17 | 0.895 16 | 0.222 16 | 0.537 12 | 0.307 16 | 0.180 5 | 0.625 14 | 0.000 1 | 0.000 12 | 0.591 17 | 0.609 14 | 0.398 15 | 0.000 1 | 0.766 17 | 0.014 16 | 0.638 17 | 0.000 1 | 0.377 13 | 0.004 13 | 0.206 13 | 0.609 17 | 0.465 5 | ||||||||||||||||||||||||||||
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
LGround | ![]() | 0.272 15 | 0.485 15 | 0.184 15 | 0.106 15 | 0.476 11 | 0.077 10 | 0.218 8 | 0.000 3 | 0.000 7 | 0.000 1 | 0.547 2 | 0.295 11 | 0.540 5 | 0.746 10 | 0.745 15 | 0.058 16 | 0.112 16 | 0.005 1 | 0.658 11 | 0.077 15 | 0.000 9 | 0.322 14 | 0.178 16 | 0.512 11 | 0.190 13 | 0.199 2 | 0.277 15 | 0.000 1 | 0.000 3 | 0.173 7 | 0.399 12 | 0.000 11 | 0.000 1 | 0.039 16 | 0.000 3 | 0.858 14 | 0.085 7 | 0.676 11 | 0.002 5 | 0.103 6 | 0.498 8 | 0.323 14 | 0.703 12 | 0.000 1 | 0.000 2 | 0.296 15 | 0.549 12 | 0.216 1 | 0.702 6 | 0.768 14 | 0.718 14 | 0.028 10 | 0.092 16 | 0.786 16 | 0.000 1 | 0.000 11 | 0.453 16 | 0.022 5 | 0.251 17 | 0.252 9 | 0.572 15 | 0.348 14 | 0.321 11 | 0.514 7 | 0.063 15 | 0.279 16 | 0.552 15 | 0.000 7 | 0.019 16 | 0.932 15 | 0.132 15 | 0.000 1 | 0.000 12 | 0.000 15 | 0.156 17 | 0.457 15 | 0.623 12 | 0.518 14 | 0.265 16 | 0.358 11 | 0.381 15 | 0.395 14 | 0.000 4 | 0.000 1 | 0.127 17 | 0.012 8 | 0.051 1 | 0.000 12 | 0.000 4 | 0.886 13 | 0.014 14 | 0.437 17 | 0.179 8 | 0.244 15 | 0.826 15 | 0.000 12 | 0.000 1 | 0.599 10 | 0.136 1 | 0.085 3 | 0.000 4 | 0.000 1 | 0.000 11 | 0.565 13 | 0.612 13 | 0.143 5 | 0.207 15 | 0.566 14 | 0.232 15 | 0.446 15 | 0.127 4 | 0.708 15 | 0.000 6 | 0.384 9 | 0.000 1 | 0.000 8 | 0.000 3 | 0.402 14 | 0.000 5 | 0.059 7 | 0.000 1 | 0.525 15 | 0.566 11 | 0.229 12 | 0.659 15 | 0.000 10 | 0.000 1 | 0.265 15 | 0.446 14 | 0.147 16 | 0.720 17 | 0.597 8 | 0.066 14 | 0.000 11 | 0.187 9 | 0.000 1 | 0.726 13 | 0.467 17 | 0.134 12 | 0.000 10 | 0.413 15 | 0.629 12 | 0.000 1 | 0.363 16 | 0.055 10 | 0.022 3 | 0.000 1 | 0.626 11 | 0.000 2 | 0.000 1 | 0.323 15 | 0.479 17 | 0.154 16 | 0.117 15 | 0.028 16 | 0.901 15 | 0.243 15 | 0.415 16 | 0.295 17 | 0.143 6 | 0.610 16 | 0.000 1 | 0.000 12 | 0.777 12 | 0.397 17 | 0.324 16 | 0.000 1 | 0.778 15 | 0.179 8 | 0.702 16 | 0.000 1 | 0.274 16 | 0.404 4 | 0.233 10 | 0.622 15 | 0.398 7 | ||||||||||||||||||||||||||||
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
AWCS | 0.305 14 | 0.508 14 | 0.225 14 | 0.142 11 | 0.463 13 | 0.063 13 | 0.195 9 | 0.000 3 | 0.000 7 | 0.000 1 | 0.467 3 | 0.551 3 | 0.504 8 | 0.773 6 | 0.764 14 | 0.142 13 | 0.029 17 | 0.000 3 | 0.626 13 | 0.100 11 | 0.000 9 | 0.360 13 | 0.179 15 | 0.507 13 | 0.137 15 | 0.006 8 | 0.300 12 | 0.000 1 | 0.000 3 | 0.172 8 | 0.364 15 | 0.512 9 | 0.000 1 | 0.056 14 | 0.000 3 | 0.865 13 | 0.093 4 | 0.634 17 | 0.000 7 | 0.071 13 | 0.396 14 | 0.296 16 | 0.876 9 | 0.000 1 | 0.000 2 | 0.373 13 | 0.436 16 | 0.063 9 | 0.749 2 | 0.877 10 | 0.721 12 | 0.131 3 | 0.124 14 | 0.804 15 | 0.000 1 | 0.000 11 | 0.515 12 | 0.010 6 | 0.452 10 | 0.252 9 | 0.578 14 | 0.417 8 | 0.179 17 | 0.484 10 | 0.171 7 | 0.337 14 | 0.606 12 | 0.000 7 | 0.115 10 | 0.937 14 | 0.142 9 | 0.000 1 | 0.008 11 | 0.000 15 | 0.157 16 | 0.484 14 | 0.402 17 | 0.501 15 | 0.339 9 | 0.553 7 | 0.529 3 | 0.478 12 | 0.000 4 | 0.000 1 | 0.404 10 | 0.001 10 | 0.022 13 | 0.077 9 | 0.000 4 | 0.894 12 | 0.219 7 | 0.628 7 | 0.093 15 | 0.305 14 | 0.886 1 | 0.233 9 | 0.000 1 | 0.603 9 | 0.112 6 | 0.023 9 | 0.000 4 | 0.000 1 | 0.000 11 | 0.741 6 | 0.664 8 | 0.097 15 | 0.253 14 | 0.782 10 | 0.264 11 | 0.523 11 | 0.154 2 | 0.707 16 | 0.000 6 | 0.411 8 | 0.000 1 | 0.000 8 | 0.000 3 | 0.332 16 | 0.000 5 | 0.000 9 | 0.000 1 | 0.602 7 | 0.595 10 | 0.185 13 | 0.656 16 | 0.159 6 | 0.000 1 | 0.355 11 | 0.424 15 | 0.154 15 | 0.729 15 | 0.516 10 | 0.220 10 | 0.620 3 | 0.084 13 | 0.000 1 | 0.707 14 | 0.651 13 | 0.173 5 | 0.014 9 | 0.381 17 | 0.582 14 | 0.000 1 | 0.619 3 | 0.049 12 | 0.000 7 | 0.000 1 | 0.702 4 | 0.000 2 | 0.000 1 | 0.302 16 | 0.489 15 | 0.317 13 | 0.334 7 | 0.392 7 | 0.922 14 | 0.254 13 | 0.533 13 | 0.394 13 | 0.129 14 | 0.613 15 | 0.000 1 | 0.000 12 | 0.820 5 | 0.649 11 | 0.749 13 | 0.000 1 | 0.782 14 | 0.282 6 | 0.863 6 | 0.000 1 | 0.288 15 | 0.006 12 | 0.220 11 | 0.633 14 | 0.542 3 | |||||||||||||||||||||||||||||
: Long-Tailed 3D Semantic Segmentation with Adaptive Weight Constraint and Sampling. ICRA 2024 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
CeCo | 0.340 7 | 0.551 9 | 0.247 13 | 0.181 6 | 0.475 12 | 0.057 15 | 0.142 12 | 0.000 3 | 0.000 7 | 0.000 1 | 0.387 6 | 0.463 6 | 0.499 9 | 0.924 2 | 0.774 11 | 0.213 6 | 0.257 13 | 0.000 3 | 0.546 15 | 0.100 11 | 0.006 8 | 0.615 2 | 0.177 17 | 0.534 7 | 0.246 6 | 0.000 9 | 0.400 5 | 0.000 1 | 0.338 1 | 0.006 16 | 0.484 5 | 0.609 5 | 0.000 1 | 0.083 11 | 0.000 3 | 0.873 9 | 0.089 5 | 0.661 14 | 0.000 7 | 0.048 15 | 0.560 4 | 0.408 6 | 0.892 8 | 0.000 1 | 0.000 2 | 0.586 1 | 0.616 8 | 0.000 10 | 0.692 8 | 0.900 8 | 0.721 12 | 0.162 1 | 0.228 6 | 0.860 11 | 0.000 1 | 0.000 11 | 0.575 5 | 0.083 3 | 0.550 4 | 0.347 4 | 0.624 13 | 0.410 10 | 0.360 9 | 0.740 3 | 0.109 13 | 0.321 15 | 0.660 8 | 0.000 7 | 0.121 9 | 0.939 13 | 0.143 8 | 0.000 1 | 0.400 2 | 0.003 13 | 0.190 11 | 0.564 6 | 0.652 10 | 0.615 11 | 0.421 5 | 0.304 13 | 0.579 1 | 0.547 5 | 0.000 4 | 0.000 1 | 0.296 14 | 0.000 11 | 0.030 9 | 0.096 7 | 0.000 4 | 0.916 4 | 0.037 13 | 0.551 12 | 0.171 9 | 0.376 7 | 0.865 7 | 0.286 5 | 0.000 1 | 0.633 5 | 0.102 12 | 0.027 8 | 0.011 3 | 0.000 1 | 0.000 11 | 0.474 14 | 0.742 5 | 0.133 7 | 0.311 13 | 0.824 8 | 0.242 13 | 0.503 14 | 0.068 9 | 0.828 9 | 0.000 6 | 0.429 7 | 0.000 1 | 0.063 5 | 0.000 3 | 0.781 2 | 0.000 5 | 0.000 9 | 0.000 1 | 0.665 2 | 0.633 6 | 0.450 6 | 0.818 2 | 0.000 10 | 0.000 1 | 0.429 5 | 0.532 7 | 0.226 13 | 0.825 11 | 0.510 11 | 0.377 5 | 0.709 2 | 0.079 14 | 0.000 1 | 0.753 5 | 0.683 8 | 0.102 15 | 0.063 5 | 0.401 16 | 0.620 13 | 0.000 1 | 0.619 3 | 0.000 14 | 0.000 7 | 0.000 1 | 0.595 13 | 0.000 2 | 0.000 1 | 0.345 14 | 0.564 6 | 0.411 8 | 0.603 1 | 0.384 8 | 0.945 9 | 0.266 11 | 0.643 5 | 0.367 14 | 0.304 1 | 0.663 10 | 0.000 1 | 0.010 7 | 0.726 15 | 0.767 7 | 0.898 3 | 0.000 1 | 0.784 13 | 0.435 1 | 0.861 7 | 0.000 1 | 0.447 11 | 0.000 15 | 0.257 7 | 0.656 11 | 0.377 10 | |||||||||||||||||||||||||||||
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
OctFormer ScanNet200 | ![]() | 0.326 13 | 0.539 10 | 0.265 10 | 0.131 12 | 0.499 6 | 0.110 4 | 0.522 3 | 0.000 3 | 0.000 7 | 0.000 1 | 0.318 11 | 0.427 7 | 0.455 15 | 0.743 11 | 0.765 13 | 0.175 11 | 0.842 4 | 0.000 3 | 0.828 5 | 0.204 4 | 0.033 6 | 0.429 11 | 0.335 6 | 0.601 2 | 0.312 3 | 0.000 9 | 0.357 10 | 0.000 1 | 0.000 3 | 0.047 11 | 0.423 9 | 0.000 11 | 0.000 1 | 0.105 9 | 0.000 3 | 0.873 9 | 0.079 9 | 0.670 12 | 0.000 7 | 0.117 5 | 0.471 13 | 0.432 3 | 0.829 11 | 0.000 1 | 0.000 2 | 0.584 2 | 0.417 17 | 0.089 6 | 0.684 9 | 0.837 12 | 0.705 16 | 0.021 12 | 0.178 11 | 0.892 6 | 0.000 1 | 0.028 8 | 0.505 13 | 0.000 7 | 0.457 9 | 0.200 14 | 0.662 4 | 0.412 9 | 0.244 15 | 0.496 8 | 0.000 17 | 0.451 8 | 0.626 9 | 0.000 7 | 0.102 11 | 0.943 9 | 0.138 13 | 0.000 1 | 0.000 12 | 0.149 8 | 0.291 3 | 0.534 9 | 0.722 7 | 0.632 7 | 0.331 10 | 0.253 14 | 0.453 11 | 0.487 11 | 0.000 4 | 0.000 1 | 0.479 6 | 0.000 11 | 0.022 13 | 0.000 12 | 0.000 4 | 0.900 10 | 0.128 11 | 0.684 3 | 0.164 10 | 0.413 4 | 0.854 10 | 0.000 12 | 0.000 1 | 0.512 16 | 0.074 15 | 0.003 11 | 0.000 4 | 0.000 1 | 0.000 11 | 0.469 15 | 0.613 12 | 0.132 8 | 0.529 7 | 0.871 3 | 0.227 16 | 0.582 7 | 0.026 17 | 0.787 12 | 0.000 6 | 0.339 15 | 0.000 1 | 0.000 8 | 0.000 3 | 0.626 7 | 0.000 5 | 0.029 8 | 0.000 1 | 0.587 9 | 0.612 8 | 0.411 7 | 0.724 10 | 0.000 10 | 0.000 1 | 0.407 6 | 0.552 5 | 0.513 3 | 0.849 10 | 0.655 4 | 0.408 4 | 0.000 11 | 0.296 2 | 0.000 1 | 0.686 15 | 0.645 14 | 0.145 8 | 0.022 8 | 0.414 14 | 0.633 11 | 0.000 1 | 0.637 2 | 0.224 3 | 0.000 7 | 0.000 1 | 0.650 8 | 0.000 2 | 0.000 1 | 0.622 9 | 0.535 12 | 0.343 12 | 0.483 3 | 0.230 13 | 0.943 10 | 0.289 10 | 0.618 7 | 0.596 5 | 0.140 8 | 0.679 8 | 0.000 1 | 0.022 6 | 0.783 11 | 0.620 12 | 0.906 1 | 0.000 1 | 0.806 8 | 0.137 10 | 0.865 5 | 0.000 1 | 0.378 12 | 0.000 15 | 0.168 15 | 0.680 8 | 0.227 13 | ||||||||||||||||||||||||||||
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
PPT-SpUNet-F.T. | 0.332 12 | 0.556 6 | 0.270 7 | 0.123 14 | 0.519 4 | 0.091 7 | 0.349 4 | 0.000 3 | 0.000 7 | 0.000 1 | 0.339 9 | 0.383 10 | 0.498 10 | 0.833 4 | 0.807 4 | 0.241 4 | 0.584 9 | 0.000 3 | 0.755 7 | 0.124 8 | 0.000 9 | 0.608 3 | 0.330 8 | 0.530 9 | 0.314 2 | 0.000 9 | 0.374 8 | 0.000 1 | 0.000 3 | 0.197 5 | 0.459 7 | 0.000 11 | 0.000 1 | 0.117 6 | 0.000 3 | 0.876 7 | 0.095 2 | 0.682 9 | 0.000 7 | 0.086 8 | 0.518 7 | 0.433 2 | 0.930 4 | 0.000 1 | 0.000 2 | 0.563 3 | 0.542 14 | 0.077 7 | 0.715 4 | 0.858 11 | 0.756 5 | 0.008 16 | 0.171 12 | 0.874 8 | 0.000 1 | 0.039 7 | 0.550 11 | 0.000 7 | 0.545 5 | 0.256 8 | 0.657 8 | 0.453 4 | 0.351 10 | 0.449 11 | 0.213 6 | 0.392 12 | 0.611 11 | 0.000 7 | 0.037 15 | 0.946 6 | 0.138 13 | 0.000 1 | 0.000 12 | 0.063 11 | 0.308 2 | 0.537 8 | 0.796 5 | 0.673 4 | 0.323 11 | 0.392 10 | 0.400 14 | 0.509 7 | 0.000 4 | 0.000 1 | 0.649 1 | 0.000 11 | 0.023 12 | 0.000 12 | 0.000 4 | 0.914 6 | 0.002 16 | 0.506 16 | 0.163 11 | 0.359 8 | 0.872 5 | 0.000 12 | 0.000 1 | 0.623 7 | 0.112 6 | 0.001 12 | 0.000 4 | 0.000 1 | 0.021 9 | 0.753 5 | 0.565 15 | 0.150 4 | 0.579 4 | 0.806 9 | 0.267 9 | 0.616 4 | 0.042 14 | 0.783 13 | 0.000 6 | 0.374 11 | 0.000 1 | 0.000 8 | 0.000 3 | 0.620 8 | 0.000 5 | 0.000 9 | 0.000 1 | 0.572 13 | 0.634 5 | 0.350 9 | 0.792 5 | 0.000 10 | 0.000 1 | 0.376 9 | 0.535 6 | 0.378 6 | 0.855 7 | 0.672 3 | 0.074 13 | 0.000 11 | 0.185 10 | 0.000 1 | 0.727 12 | 0.660 12 | 0.076 17 | 0.000 10 | 0.432 12 | 0.646 10 | 0.000 1 | 0.594 8 | 0.006 13 | 0.000 7 | 0.000 1 | 0.658 7 | 0.000 2 | 0.000 1 | 0.661 4 | 0.549 10 | 0.300 14 | 0.291 8 | 0.045 14 | 0.942 11 | 0.304 8 | 0.600 8 | 0.572 7 | 0.135 12 | 0.695 5 | 0.000 1 | 0.008 9 | 0.793 9 | 0.942 2 | 0.899 2 | 0.000 1 | 0.816 6 | 0.181 7 | 0.897 2 | 0.000 1 | 0.679 4 | 0.223 8 | 0.264 5 | 0.691 5 | 0.345 12 | |||||||||||||||||||||||||||||
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
L3DETR-ScanNet_200 | 0.336 8 | 0.533 11 | 0.279 6 | 0.155 10 | 0.508 5 | 0.073 11 | 0.101 17 | 0.000 3 | 0.058 6 | 0.000 1 | 0.294 14 | 0.233 14 | 0.548 4 | 0.927 1 | 0.788 10 | 0.264 2 | 0.463 11 | 0.000 3 | 0.638 12 | 0.098 13 | 0.014 7 | 0.411 12 | 0.226 13 | 0.525 10 | 0.225 9 | 0.010 7 | 0.397 6 | 0.000 1 | 0.000 3 | 0.192 6 | 0.380 14 | 0.598 6 | 0.000 1 | 0.117 6 | 0.000 3 | 0.883 6 | 0.082 8 | 0.689 4 | 0.000 7 | 0.032 17 | 0.549 6 | 0.417 4 | 0.910 5 | 0.000 1 | 0.000 2 | 0.448 8 | 0.613 9 | 0.000 10 | 0.697 7 | 0.960 3 | 0.759 4 | 0.158 2 | 0.293 3 | 0.883 7 | 0.000 1 | 0.312 3 | 0.583 4 | 0.079 4 | 0.422 11 | 0.068 17 | 0.660 7 | 0.418 7 | 0.298 12 | 0.430 12 | 0.114 11 | 0.526 5 | 0.776 3 | 0.051 3 | 0.679 3 | 0.946 6 | 0.152 7 | 0.000 1 | 0.183 8 | 0.000 15 | 0.211 8 | 0.511 10 | 0.409 16 | 0.565 12 | 0.355 8 | 0.448 8 | 0.512 5 | 0.557 3 | 0.000 4 | 0.000 1 | 0.420 9 | 0.000 11 | 0.007 17 | 0.104 6 | 0.000 4 | 0.125 17 | 0.330 3 | 0.514 15 | 0.146 12 | 0.321 13 | 0.860 8 | 0.174 11 | 0.000 1 | 0.629 6 | 0.075 14 | 0.000 14 | 0.000 4 | 0.000 1 | 0.002 10 | 0.671 8 | 0.712 7 | 0.141 6 | 0.339 12 | 0.856 4 | 0.261 12 | 0.529 10 | 0.067 10 | 0.835 6 | 0.000 6 | 0.369 12 | 0.000 1 | 0.259 2 | 0.000 3 | 0.629 6 | 0.000 5 | 0.487 1 | 0.000 1 | 0.579 11 | 0.646 4 | 0.107 17 | 0.720 11 | 0.122 7 | 0.000 1 | 0.333 14 | 0.505 10 | 0.303 9 | 0.908 3 | 0.503 13 | 0.565 2 | 0.074 8 | 0.324 1 | 0.000 1 | 0.740 8 | 0.661 11 | 0.109 13 | 0.000 10 | 0.427 13 | 0.563 17 | 0.000 1 | 0.579 11 | 0.108 8 | 0.000 7 | 0.000 1 | 0.664 6 | 0.000 2 | 0.000 1 | 0.641 7 | 0.539 11 | 0.416 7 | 0.515 2 | 0.256 11 | 0.940 12 | 0.312 6 | 0.209 17 | 0.620 3 | 0.138 11 | 0.636 11 | 0.000 1 | 0.000 12 | 0.775 13 | 0.861 5 | 0.765 12 | 0.000 1 | 0.801 9 | 0.119 11 | 0.860 8 | 0.000 1 | 0.687 2 | 0.001 14 | 0.192 14 | 0.679 9 | 0.699 1 | |||||||||||||||||||||||||||||
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
GSTran | 0.334 10 | 0.533 12 | 0.250 12 | 0.179 8 | 0.487 8 | 0.041 16 | 0.139 13 | 0.003 1 | 0.273 5 | 0.000 1 | 0.273 16 | 0.189 16 | 0.465 12 | 0.704 14 | 0.794 8 | 0.198 8 | 0.831 5 | 0.000 3 | 0.712 8 | 0.055 16 | 0.063 5 | 0.518 6 | 0.306 9 | 0.459 16 | 0.217 10 | 0.028 4 | 0.282 14 | 0.000 1 | 0.000 3 | 0.044 12 | 0.405 11 | 0.558 8 | 0.000 1 | 0.080 12 | 0.000 3 | 0.873 9 | 0.020 16 | 0.684 7 | 0.000 7 | 0.075 12 | 0.496 9 | 0.363 9 | 0.651 15 | 0.000 1 | 0.000 2 | 0.425 9 | 0.648 5 | 0.000 10 | 0.669 11 | 0.914 6 | 0.741 10 | 0.009 15 | 0.200 9 | 0.864 9 | 0.000 1 | 0.000 11 | 0.560 9 | 0.000 7 | 0.357 14 | 0.233 12 | 0.633 11 | 0.408 11 | 0.411 4 | 0.320 16 | 0.242 5 | 0.440 9 | 0.598 14 | 0.047 4 | 0.205 8 | 0.940 10 | 0.139 11 | 0.000 1 | 0.372 4 | 0.138 9 | 0.191 10 | 0.495 11 | 0.618 13 | 0.624 9 | 0.321 12 | 0.595 4 | 0.496 7 | 0.499 8 | 0.000 4 | 0.000 1 | 0.340 12 | 0.014 6 | 0.032 7 | 0.136 4 | 0.000 4 | 0.903 8 | 0.279 5 | 0.601 9 | 0.198 5 | 0.345 11 | 0.849 11 | 0.260 6 | 0.000 1 | 0.573 14 | 0.072 17 | 0.060 5 | 0.000 4 | 0.000 1 | 0.089 7 | 0.838 4 | 0.775 4 | 0.125 11 | 0.381 11 | 0.752 13 | 0.274 5 | 0.517 13 | 0.032 15 | 0.841 5 | 0.000 6 | 0.354 14 | 0.000 1 | 0.047 6 | 0.000 3 | 0.439 13 | 0.787 3 | 0.252 4 | 0.000 1 | 0.512 16 | 0.507 16 | 0.158 16 | 0.717 12 | 0.000 10 | 0.000 1 | 0.337 12 | 0.483 13 | 0.570 1 | 0.853 8 | 0.614 7 | 0.121 11 | 0.070 9 | 0.229 7 | 0.000 1 | 0.732 11 | 0.773 2 | 0.193 3 | 0.000 10 | 0.606 7 | 0.791 5 | 0.000 1 | 0.593 9 | 0.000 14 | 0.010 5 | 0.000 1 | 0.574 16 | 0.000 2 | 0.000 1 | 0.507 12 | 0.554 9 | 0.361 11 | 0.136 13 | 0.608 3 | 0.948 7 | 0.304 8 | 0.593 10 | 0.533 8 | 0.011 16 | 0.634 12 | 0.000 1 | 0.060 3 | 0.821 4 | 0.613 13 | 0.797 10 | 0.000 1 | 0.799 11 | 0.036 13 | 0.782 14 | 0.000 1 | 0.609 7 | 0.423 3 | 0.133 17 | 0.647 12 | 0.213 15 | |||||||||||||||||||||||||||||
PTv3 ScanNet200 | 0.393 3 | 0.592 3 | 0.330 2 | 0.216 3 | 0.520 3 | 0.109 5 | 0.108 16 | 0.000 3 | 0.337 1 | 0.000 1 | 0.310 12 | 0.394 9 | 0.494 11 | 0.753 9 | 0.848 2 | 0.256 3 | 0.717 8 | 0.000 3 | 0.842 4 | 0.192 5 | 0.065 3 | 0.449 10 | 0.346 4 | 0.546 6 | 0.190 13 | 0.000 9 | 0.384 7 | 0.000 1 | 0.000 3 | 0.218 4 | 0.505 2 | 0.791 3 | 0.000 1 | 0.136 4 | 0.000 3 | 0.903 2 | 0.073 12 | 0.687 6 | 0.000 7 | 0.168 2 | 0.551 5 | 0.387 7 | 0.941 3 | 0.000 1 | 0.000 2 | 0.397 12 | 0.654 3 | 0.000 10 | 0.714 5 | 0.759 15 | 0.752 7 | 0.118 4 | 0.264 4 | 0.926 3 | 0.000 1 | 0.048 6 | 0.575 5 | 0.000 7 | 0.597 2 | 0.366 2 | 0.755 1 | 0.469 2 | 0.474 3 | 0.798 2 | 0.140 10 | 0.617 3 | 0.692 7 | 0.000 7 | 0.592 4 | 0.971 2 | 0.188 4 | 0.000 1 | 0.133 9 | 0.593 2 | 0.349 1 | 0.650 3 | 0.717 8 | 0.699 3 | 0.455 2 | 0.790 2 | 0.523 4 | 0.636 1 | 0.301 1 | 0.000 1 | 0.622 2 | 0.000 11 | 0.017 15 | 0.259 3 | 0.000 4 | 0.921 3 | 0.337 1 | 0.733 2 | 0.210 4 | 0.514 2 | 0.860 8 | 0.407 1 | 0.000 1 | 0.688 2 | 0.109 8 | 0.000 14 | 0.000 4 | 0.000 1 | 0.151 5 | 0.671 8 | 0.782 2 | 0.115 13 | 0.641 2 | 0.903 2 | 0.349 1 | 0.616 4 | 0.088 7 | 0.832 8 | 0.000 6 | 0.480 2 | 0.000 1 | 0.428 1 | 0.000 3 | 0.497 10 | 0.000 5 | 0.000 9 | 0.000 1 | 0.662 3 | 0.690 2 | 0.612 1 | 0.828 1 | 0.575 1 | 0.000 1 | 0.404 7 | 0.644 2 | 0.325 7 | 0.887 4 | 0.728 1 | 0.009 16 | 0.134 7 | 0.026 17 | 0.000 1 | 0.761 3 | 0.731 4 | 0.172 6 | 0.077 4 | 0.528 8 | 0.727 7 | 0.000 1 | 0.603 5 | 0.220 5 | 0.022 3 | 0.000 1 | 0.740 1 | 0.000 2 | 0.000 1 | 0.661 4 | 0.586 2 | 0.566 4 | 0.436 4 | 0.531 5 | 0.978 3 | 0.457 2 | 0.708 3 | 0.583 6 | 0.141 7 | 0.748 3 | 0.000 1 | 0.026 5 | 0.822 3 | 0.871 4 | 0.879 5 | 0.000 1 | 0.851 2 | 0.405 2 | 0.914 1 | 0.000 1 | 0.682 3 | 0.000 15 | 0.281 4 | 0.738 3 | 0.463 6 | |||||||||||||||||||||||||||||
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao: Point Transformer V3: Simpler, Faster, Stronger. CVPR 2024 (Oral) | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
PonderV2 ScanNet200 | 0.346 6 | 0.552 8 | 0.270 8 | 0.175 9 | 0.497 7 | 0.070 12 | 0.239 7 | 0.000 3 | 0.000 7 | 0.000 1 | 0.232 17 | 0.412 8 | 0.584 2 | 0.842 3 | 0.804 5 | 0.212 7 | 0.540 10 | 0.000 3 | 0.433 16 | 0.106 10 | 0.000 9 | 0.590 5 | 0.290 12 | 0.548 5 | 0.243 7 | 0.000 9 | 0.356 11 | 0.000 1 | 0.000 3 | 0.062 10 | 0.398 13 | 0.441 10 | 0.000 1 | 0.104 10 | 0.000 3 | 0.888 5 | 0.076 11 | 0.682 9 | 0.030 3 | 0.094 7 | 0.491 11 | 0.351 12 | 0.869 10 | 0.000 1 | 0.063 1 | 0.403 11 | 0.700 2 | 0.000 10 | 0.660 13 | 0.881 9 | 0.761 3 | 0.050 8 | 0.186 10 | 0.852 13 | 0.000 1 | 0.007 9 | 0.570 8 | 0.100 2 | 0.565 3 | 0.326 6 | 0.641 10 | 0.431 6 | 0.290 14 | 0.621 6 | 0.259 3 | 0.408 11 | 0.622 10 | 0.125 2 | 0.082 12 | 0.950 5 | 0.179 5 | 0.000 1 | 0.263 6 | 0.424 5 | 0.193 9 | 0.558 7 | 0.880 4 | 0.545 13 | 0.375 7 | 0.727 3 | 0.445 12 | 0.499 8 | 0.000 4 | 0.000 1 | 0.475 7 | 0.002 9 | 0.034 6 | 0.083 8 | 0.000 4 | 0.924 2 | 0.290 4 | 0.636 6 | 0.115 14 | 0.400 5 | 0.874 4 | 0.186 10 | 0.000 1 | 0.611 8 | 0.128 3 | 0.113 2 | 0.000 4 | 0.000 1 | 0.000 11 | 0.584 12 | 0.636 10 | 0.103 14 | 0.385 10 | 0.843 6 | 0.283 4 | 0.603 6 | 0.080 8 | 0.825 10 | 0.000 6 | 0.377 10 | 0.000 1 | 0.000 8 | 0.000 3 | 0.457 11 | 0.000 5 | 0.000 9 | 0.000 1 | 0.574 12 | 0.608 9 | 0.481 4 | 0.792 5 | 0.394 5 | 0.000 1 | 0.357 10 | 0.503 11 | 0.261 10 | 0.817 13 | 0.504 12 | 0.304 7 | 0.472 4 | 0.115 11 | 0.000 1 | 0.750 7 | 0.677 9 | 0.202 2 | 0.000 10 | 0.509 9 | 0.729 6 | 0.000 1 | 0.519 12 | 0.000 14 | 0.000 7 | 0.000 1 | 0.620 12 | 0.000 2 | 0.000 1 | 0.660 6 | 0.560 7 | 0.486 6 | 0.384 6 | 0.346 10 | 0.952 5 | 0.247 14 | 0.667 4 | 0.436 12 | 0.269 3 | 0.691 6 | 0.000 1 | 0.010 7 | 0.787 10 | 0.889 3 | 0.880 4 | 0.000 1 | 0.810 7 | 0.336 4 | 0.860 8 | 0.000 1 | 0.606 8 | 0.009 11 | 0.248 9 | 0.681 7 | 0.392 9 | |||||||||||||||||||||||||||||
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
ODIN - Sem200 | ![]() | 0.368 4 | 0.562 4 | 0.297 4 | 0.207 4 | 0.380 17 | 0.196 1 | 0.828 2 | 0.000 3 | 0.321 2 | 0.000 1 | 0.400 5 | 0.775 1 | 0.460 13 | 0.501 17 | 0.769 12 | 0.065 15 | 0.870 3 | 0.000 3 | 0.913 1 | 0.213 3 | 0.000 9 | 0.000 17 | 0.389 2 | 0.554 4 | 0.312 3 | 0.000 9 | 0.591 1 | 0.000 1 | 0.000 3 | 0.491 1 | 0.487 3 | 0.894 2 | 0.000 1 | 0.378 2 | 0.303 1 | 0.796 17 | 0.088 6 | 0.669 13 | 0.081 1 | 0.216 1 | 0.256 17 | 0.334 13 | 0.898 7 | 0.000 1 | 0.000 2 | 0.370 14 | 0.599 10 | 0.000 10 | 0.581 16 | 0.988 2 | 0.749 8 | 0.090 6 | 0.242 5 | 0.921 4 | 0.000 1 | 0.202 5 | 0.609 2 | 0.000 7 | 0.655 1 | 0.214 13 | 0.654 9 | 0.346 15 | 0.408 7 | 0.485 9 | 0.169 8 | 0.631 2 | 0.704 6 | 0.000 7 | 0.814 1 | 0.940 10 | 0.127 16 | 0.000 1 | 0.000 12 | 0.462 4 | 0.227 6 | 0.641 4 | 0.885 3 | 0.657 5 | 0.434 3 | 0.000 17 | 0.550 2 | 0.393 15 | 0.000 4 | 0.000 1 | 0.590 4 | 0.000 11 | 0.048 2 | 0.077 9 | 0.000 4 | 0.784 16 | 0.131 10 | 0.557 10 | 0.316 2 | 0.359 8 | 0.833 14 | 0.373 2 | 0.000 1 | 0.661 4 | 0.108 9 | 0.001 12 | 0.000 4 | 0.000 1 | 0.301 3 | 0.612 11 | 0.565 15 | 0.129 10 | 0.482 8 | 0.468 16 | 0.274 5 | 0.561 8 | 0.376 1 | 0.912 2 | 0.181 1 | 0.440 6 | 0.000 1 | 0.166 4 | 0.000 3 | 0.641 5 | 0.000 5 | 0.426 2 | 0.000 1 | 0.642 5 | 0.626 7 | 0.259 11 | 0.787 8 | 0.429 4 | 0.000 1 | 0.589 1 | 0.523 8 | 0.246 11 | 0.857 6 | 0.000 17 | 0.228 9 | 0.000 11 | 0.265 4 | 0.000 1 | 0.752 6 | 0.832 1 | 0.090 16 | 0.157 1 | 0.791 1 | 0.578 16 | 0.000 1 | 0.373 15 | 0.539 1 | 0.000 7 | 0.000 1 | 0.685 5 | 0.000 2 | 0.000 1 | 0.632 8 | 0.575 3 | 0.663 1 | 0.152 11 | 0.358 9 | 0.926 13 | 0.397 3 | 0.454 15 | 0.610 4 | 0.119 15 | 0.685 7 | 0.000 1 | 0.000 12 | 0.803 8 | 0.740 9 | 0.441 14 | 0.000 1 | 0.800 10 | 0.000 17 | 0.871 3 | 0.000 1 | 0.220 17 | 0.487 1 | 0.862 1 | 0.682 6 | 0.054 17 | ||||||||||||||||||||||||||||
Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki: ODIN: A Single Model for 2D and 3D Segmentation. CVPR 2024 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
ALS-MinkowskiNet | ![]() | 0.414 2 | 0.610 2 | 0.322 3 | 0.271 2 | 0.542 2 | 0.153 3 | 0.159 11 | 0.000 3 | 0.000 7 | 0.000 1 | 0.404 4 | 0.503 5 | 0.532 6 | 0.672 16 | 0.804 5 | 0.285 1 | 0.888 2 | 0.000 3 | 0.900 2 | 0.226 2 | 0.087 2 | 0.598 4 | 0.342 5 | 0.671 1 | 0.217 10 | 0.087 3 | 0.449 4 | 0.000 1 | 0.000 3 | 0.253 3 | 0.477 6 | 1.000 1 | 0.000 1 | 0.118 5 | 0.000 3 | 0.905 1 | 0.071 13 | 0.710 2 | 0.076 2 | 0.047 16 | 0.665 1 | 0.376 8 | 0.981 1 | 0.000 1 | 0.000 2 | 0.466 7 | 0.632 7 | 0.113 4 | 0.769 1 | 0.956 4 | 0.795 2 | 0.031 9 | 0.314 1 | 0.936 1 | 0.000 1 | 0.390 2 | 0.601 3 | 0.000 7 | 0.458 8 | 0.366 2 | 0.719 3 | 0.440 5 | 0.564 1 | 0.699 4 | 0.314 1 | 0.464 7 | 0.784 2 | 0.200 1 | 0.283 6 | 0.973 1 | 0.142 9 | 0.000 1 | 0.250 7 | 0.285 6 | 0.220 7 | 0.718 1 | 0.752 6 | 0.723 2 | 0.460 1 | 0.248 15 | 0.475 10 | 0.463 13 | 0.000 4 | 0.000 1 | 0.446 8 | 0.021 5 | 0.025 11 | 0.285 1 | 0.000 4 | 0.972 1 | 0.149 8 | 0.769 1 | 0.230 3 | 0.535 1 | 0.879 2 | 0.252 8 | 0.000 1 | 0.693 1 | 0.129 2 | 0.000 14 | 0.000 4 | 0.000 1 | 0.447 1 | 0.958 1 | 0.662 9 | 0.159 2 | 0.598 3 | 0.780 11 | 0.344 2 | 0.646 3 | 0.106 6 | 0.893 3 | 0.135 3 | 0.455 3 | 0.000 1 | 0.194 3 | 0.259 1 | 0.726 3 | 0.475 4 | 0.000 9 | 0.000 1 | 0.741 1 | 0.865 1 | 0.571 2 | 0.817 3 | 0.445 3 | 0.000 1 | 0.506 2 | 0.630 3 | 0.230 12 | 0.916 2 | 0.728 1 | 0.635 1 | 1.000 1 | 0.252 6 | 0.000 1 | 0.804 2 | 0.697 7 | 0.137 11 | 0.043 7 | 0.717 2 | 0.807 3 | 0.000 1 | 0.510 13 | 0.245 2 | 0.000 7 | 0.000 1 | 0.709 3 | 0.000 2 | 0.000 1 | 0.703 2 | 0.572 4 | 0.646 2 | 0.223 10 | 0.531 5 | 0.984 1 | 0.397 3 | 0.813 1 | 0.798 1 | 0.135 12 | 0.800 1 | 0.000 1 | 0.097 2 | 0.832 2 | 0.752 8 | 0.842 7 | 0.000 1 | 0.852 1 | 0.149 9 | 0.846 10 | 0.000 1 | 0.666 5 | 0.359 5 | 0.252 8 | 0.777 1 | 0.690 2 | ||||||||||||||||||||||||||||
Guangda Ji, Silvan Weder, Francis Engelmann, Marc Pollefeys, Hermann Blum: ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding. arxiv | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
BFANet ScanNet200 | ![]() | 0.360 5 | 0.553 7 | 0.293 5 | 0.193 5 | 0.483 10 | 0.096 6 | 0.266 6 | 0.000 3 | 0.000 7 | 0.000 1 | 0.298 13 | 0.255 12 | 0.661 1 | 0.810 5 | 0.810 3 | 0.194 10 | 0.785 7 | 0.000 3 | 0.000 17 | 0.161 6 | 0.000 9 | 0.494 9 | 0.382 3 | 0.574 3 | 0.258 5 | 0.000 9 | 0.372 9 | 0.000 1 | 0.000 3 | 0.043 14 | 0.436 8 | 0.000 11 | 0.000 1 | 0.239 3 | 0.000 3 | 0.901 3 | 0.105 1 | 0.689 4 | 0.025 4 | 0.128 4 | 0.614 2 | 0.436 1 | 0.493 17 | 0.000 1 | 0.000 2 | 0.526 4 | 0.546 13 | 0.109 5 | 0.651 14 | 0.953 5 | 0.753 6 | 0.101 5 | 0.143 13 | 0.897 5 | 0.000 1 | 0.431 1 | 0.469 15 | 0.000 7 | 0.522 6 | 0.337 5 | 0.661 6 | 0.459 3 | 0.409 6 | 0.666 5 | 0.102 14 | 0.508 6 | 0.757 4 | 0.000 7 | 0.060 14 | 0.970 3 | 0.497 1 | 0.000 1 | 0.376 3 | 0.511 3 | 0.262 4 | 0.688 2 | 0.921 2 | 0.617 10 | 0.321 12 | 0.590 6 | 0.491 9 | 0.556 4 | 0.000 4 | 0.000 1 | 0.481 5 | 0.093 1 | 0.043 3 | 0.284 2 | 0.000 4 | 0.875 14 | 0.135 9 | 0.669 4 | 0.124 13 | 0.394 6 | 0.849 11 | 0.298 4 | 0.000 1 | 0.476 17 | 0.088 13 | 0.042 7 | 0.000 4 | 0.000 1 | 0.254 4 | 0.653 10 | 0.741 6 | 0.215 1 | 0.573 5 | 0.852 5 | 0.266 10 | 0.654 2 | 0.056 12 | 0.835 6 | 0.000 6 | 0.492 1 | 0.000 1 | 0.000 8 | 0.000 3 | 0.612 9 | 0.000 5 | 0.000 9 | 0.000 1 | 0.616 6 | 0.469 17 | 0.460 5 | 0.698 14 | 0.516 2 | 0.000 1 | 0.378 8 | 0.563 4 | 0.476 4 | 0.863 5 | 0.574 9 | 0.330 6 | 0.000 11 | 0.282 3 | 0.000 1 | 0.760 4 | 0.710 5 | 0.233 1 | 0.000 10 | 0.641 5 | 0.814 2 | 0.000 1 | 0.585 10 | 0.053 11 | 0.000 7 | 0.000 1 | 0.629 10 | 0.000 2 | 0.000 1 | 0.678 3 | 0.528 13 | 0.534 5 | 0.129 14 | 0.596 4 | 0.973 4 | 0.264 12 | 0.772 2 | 0.526 10 | 0.139 9 | 0.707 4 | 0.000 1 | 0.000 12 | 0.764 14 | 0.591 16 | 0.848 6 | 0.000 1 | 0.827 4 | 0.338 3 | 0.806 12 | 0.000 1 | 0.568 9 | 0.151 10 | 0.358 2 | 0.659 10 | 0.510 4 | ||||||||||||||||||||||||||||
Weiguang Zhao, Rui Zhang, Qiufeng Wang, Guangliang Cheng, Kaizhu Huang: BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis. CVPR 2025 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
DITR | 0.449 1 | 0.629 1 | 0.392 1 | 0.289 1 | 0.650 1 | 0.168 2 | 0.862 1 | 0.000 3 | 0.313 3 | 0.000 1 | 0.580 1 | 0.568 2 | 0.564 3 | 0.766 7 | 0.867 1 | 0.238 5 | 0.949 1 | 0.000 3 | 0.866 3 | 0.300 1 | 0.000 9 | 0.664 1 | 0.482 1 | 0.508 12 | 0.317 1 | 0.420 1 | 0.551 2 | 0.000 1 | 0.000 3 | 0.486 2 | 0.519 1 | 0.662 4 | 0.000 1 | 0.385 1 | 0.000 3 | 0.901 3 | 0.079 9 | 0.727 1 | 0.000 7 | 0.160 3 | 0.606 3 | 0.417 4 | 0.967 2 | 0.000 1 | 0.000 2 | 0.498 5 | 0.596 11 | 0.130 2 | 0.728 3 | 0.998 1 | 0.805 1 | 0.000 17 | 0.314 1 | 0.934 2 | 0.000 1 | 0.278 4 | 0.636 1 | 0.000 7 | 0.403 12 | 0.367 1 | 0.741 2 | 0.484 1 | 0.500 2 | 1.000 1 | 0.113 12 | 0.828 1 | 0.815 1 | 0.000 7 | 0.733 2 | 0.969 4 | 0.374 2 | 0.000 1 | 0.579 1 | 1.000 1 | 0.230 5 | 0.617 5 | 0.983 1 | 0.729 1 | 0.423 4 | 0.855 1 | 0.508 6 | 0.622 2 | 0.018 3 | 0.000 1 | 0.591 3 | 0.034 4 | 0.028 10 | 0.066 11 | 0.869 1 | 0.904 7 | 0.334 2 | 0.651 5 | 0.716 1 | 0.514 2 | 0.871 6 | 0.315 3 | 0.000 1 | 0.664 3 | 0.128 3 | 0.014 10 | 0.000 4 | 0.000 1 | 0.392 2 | 0.851 2 | 0.817 1 | 0.153 3 | 0.823 1 | 0.991 1 | 0.318 3 | 0.680 1 | 0.134 3 | 0.913 1 | 0.157 2 | 0.448 4 | 0.000 1 | 0.000 8 | 0.000 3 | 0.826 1 | 0.978 1 | 0.091 6 | 0.000 1 | 0.660 4 | 0.647 3 | 0.571 2 | 0.804 4 | 0.001 9 | 0.000 1 | 0.480 3 | 0.700 1 | 0.421 5 | 0.947 1 | 0.433 14 | 0.411 3 | 0.148 6 | 0.262 5 | 0.000 1 | 0.849 1 | 0.709 6 | 0.138 10 | 0.150 2 | 0.714 3 | 0.889 1 | 0.000 1 | 0.698 1 | 0.222 4 | 0.000 7 | 0.000 1 | 0.720 2 | 0.000 2 | 0.000 1 | 0.805 1 | 0.600 1 | 0.642 3 | 0.268 9 | 0.904 1 | 0.982 2 | 0.477 1 | 0.632 6 | 0.718 2 | 0.139 9 | 0.776 2 | 0.000 1 | 0.178 1 | 0.886 1 | 0.962 1 | 0.839 8 | 0.000 1 | 0.851 2 | 0.043 12 | 0.869 4 | 0.000 1 | 0.710 1 | 0.315 6 | 0.348 3 | 0.753 2 | 0.397 8 | |||||||||||||||||||||||||||||
Karim Abou Zeid, Kadir Yilmaz, Daan de Geus, Alexander Hermans, David Adrian, Timm Linder, Bastian Leibe: DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Minkowski 34D | ![]() | 0.253 16 | 0.463 16 | 0.154 17 | 0.102 16 | 0.381 16 | 0.084 8 | 0.134 15 | 0.000 3 | 0.000 7 | 0.000 1 | 0.386 7 | 0.141 17 | 0.279 17 | 0.737 12 | 0.703 16 | 0.014 17 | 0.164 15 | 0.000 3 | 0.663 10 | 0.092 14 | 0.000 9 | 0.224 15 | 0.291 11 | 0.531 8 | 0.056 17 | 0.000 9 | 0.242 16 | 0.000 1 | 0.000 3 | 0.013 15 | 0.331 16 | 0.000 11 | 0.000 1 | 0.035 17 | 0.001 2 | 0.858 14 | 0.059 14 | 0.650 16 | 0.000 7 | 0.056 14 | 0.353 15 | 0.299 15 | 0.670 13 | 0.000 1 | 0.000 2 | 0.284 16 | 0.484 15 | 0.071 8 | 0.594 15 | 0.720 16 | 0.710 15 | 0.027 11 | 0.068 17 | 0.813 14 | 0.000 1 | 0.005 10 | 0.492 14 | 0.164 1 | 0.274 16 | 0.111 16 | 0.571 16 | 0.307 17 | 0.293 13 | 0.307 17 | 0.150 9 | 0.163 17 | 0.531 16 | 0.002 6 | 0.545 5 | 0.932 15 | 0.093 17 | 0.000 1 | 0.000 12 | 0.002 14 | 0.159 15 | 0.368 17 | 0.581 15 | 0.440 17 | 0.228 17 | 0.406 9 | 0.282 17 | 0.294 16 | 0.000 4 | 0.000 1 | 0.189 16 | 0.060 2 | 0.036 5 | 0.000 12 | 0.000 4 | 0.897 11 | 0.000 17 | 0.525 14 | 0.025 17 | 0.205 17 | 0.771 17 | 0.000 12 | 0.000 1 | 0.593 11 | 0.108 9 | 0.044 6 | 0.000 4 | 0.000 1 | 0.000 11 | 0.282 17 | 0.589 14 | 0.094 16 | 0.169 16 | 0.466 17 | 0.227 16 | 0.419 17 | 0.125 5 | 0.757 14 | 0.002 4 | 0.334 16 | 0.000 1 | 0.000 8 | 0.000 3 | 0.357 15 | 0.000 5 | 0.000 9 | 0.000 1 | 0.582 10 | 0.513 14 | 0.337 10 | 0.612 17 | 0.000 10 | 0.000 1 | 0.250 16 | 0.352 17 | 0.136 17 | 0.724 16 | 0.655 4 | 0.280 8 | 0.000 11 | 0.046 16 | 0.000 1 | 0.606 17 | 0.559 15 | 0.159 7 | 0.102 3 | 0.445 10 | 0.655 9 | 0.000 1 | 0.310 17 | 0.117 6 | 0.000 7 | 0.000 1 | 0.581 15 | 0.026 1 | 0.000 1 | 0.265 17 | 0.483 16 | 0.084 17 | 0.097 17 | 0.044 15 | 0.865 17 | 0.142 17 | 0.588 11 | 0.351 15 | 0.272 2 | 0.596 17 | 0.000 1 | 0.003 10 | 0.622 16 | 0.720 10 | 0.096 17 | 0.000 1 | 0.771 16 | 0.016 15 | 0.772 15 | 0.000 1 | 0.302 14 | 0.194 9 | 0.214 12 | 0.621 16 | 0.197 16 | ||||||||||||||||||||||||||||
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019 |