Submitted anonymously.

Submission data

Full name	Deep Multimodal Networks with Residual Fusion Blocks
Description	Conventional RGB-D semantic segmentation methods adopt two-stream fusion structure which uses two modality-specific encoders to extract features from the RGB and depth data. However, they do not fully exploit the interdependencies of the encoders. We proposes a novel bottom-up interactive fusion structure and residual fusion block to formulate the interdependencies of the two encoders. https://arxiv.org/abs/1907.00135
Input Data Types	Uses Color,Uses Geometry        Uses 2D
Programming language(s)	Tensorflow
Hardware	1080ti
Submission creation date	3 Jun, 2019
Last edited	4 Jul, 2019
Last uploaded	3 Jun, 2019

2D semantic label results