| Full name | Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds |
| Description | We introduce a method for instance proposal generation for 3D point clouds. Existing techniques typically directly regress proposals in a single feed-forward step, leading to inaccurate estimation. We show that this serves as a critical bottleneck, and propose a method based on iterative bilateral filtering with learned kernels. Following the spirit of bilateral filtering, we consider both the deep feature embeddings of each point, as well as their locations in the 3D space. We show via synthetic experiments that our method brings drastic improvements when generating instance proposals for a given point of interest. We further validate our method on the challenging ScanNet benchmark, achieving the best instance segmentation performance amongst the sub-category of top-down methods. |
| Publication title | NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds |
| Publication authors | Weiwei Sun, Daniel Rebain, Renjie Liao, Vladimir Tankovich, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi |
| Publication venue | WACV 2023 |
| Publication URL | https://neuralbf.github.io/ |
| Input Data Types | Uses Color,Uses Geometry Uses 3D |
| Programming language(s) | Python/Pytorch |
| Hardware | NVIDIA 3090 |
| Website | https://neuralbf.github.io/ |
| Source code or download URL | https://neuralbf.github.io/ |
| Submission creation date | 9 Jul, 2022 |
| Last edited | 10 Jan, 2023 |