Wasserstein Distances for Stereo Disparity Estimation

Div Garg, Yan Wang, Bharath Hariharan, Mark Campbell, Kilian Weinberger, Wei-Lun (Harry) Chao

Spotlight presentation: Orals & Spotlights Track 07: Vision Applications
on 2020-12-08T07:10:00-08:00 - 2020-12-08T07:20:00-08:00
Poster Session 2 (more posters)
on 2020-12-08T09:00:00-08:00 - 2020-12-08T11:00:00-08:00
GatherTown: Vision ( Town A2 - Spot A0 )
Join GatherTown
Only iff poster is crowded, join Zoom . Authors have to start the Zoom call from their Profile page / Presentation History.
Abstract: Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values. This leads to inaccurate results when the true depth or disparity does not match any of these values. The fact that this distribution is usually learned indirectly through a regression loss causes further problems in ambiguous regions around object boundaries. We address these issues using a new neural network architecture that is capable of outputting arbitrary depth values, and a new loss function that is derived from the Wasserstein distance between the true and the predicted distributions. We validate our approach on a variety of tasks, including stereo disparity and depth estimation, and the downstream 3D object detection. Our approach drastically reduces the error in ambiguous regions, especially around object boundaries that greatly affect the localization of objects in 3D, achieving the state-of-the-art in 3D object detection for autonomous driving.

Preview Video and Chat

Chat is not available.