SENSE: a Shared Encoder Network for Scene-flow Estimation

10/27/2019 ∙ by Huaizu Jiang, et al. ∙ 17

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. With a shared encoder, we can flexibly add decoders for different tasks during training. This modular design leads to a compact and efficient model at inference time. Exploiting the interactions among these tasks allows us to introduce distillation and self-supervised losses in addition to supervised losses, which can better handle partially labeled real-world data. SENSE achieves state-of-the-art results on several optical flow benchmarks and runs as fast as networks specifically designed for optical flow. It also compares favorably against the state of the art on stereo and scene flow, while consuming much less memory.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 4

page 5

page 17

page 18

page 19

page 20

Code Repositories

SENSE

SENSE: a Shared Encoder Network for Scene-flow Estimation


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.