SENSE: a Shared Encoder Network for Scene-flow Estimation

ICCV 2019 Huaizu JiangDeqing SunVarun JampaniZhaoyang LvErik Learned-MillerJan Kautz

We introduce a compact network for holistic scene flow estimation, called SENSE, which shares common encoder features among four closely-related tasks: optical flow estimation, disparity estimation from stereo, occlusion estimation, and semantic segmentation. Our key insight is that sharing features makes the network more compact, induces better feature representations, and can better exploit interactions among these tasks to handle partially labeled data... (read more)

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.