Poster

Gated Stereo: Joint Depth Estimation From Gated and Wide-Baseline Active Stereo Cues

Stefanie Walz · Mario Bijelic · Andrea Ramazzina · Amanpreet Walia · Fahim Mannan · Felix Heide

West Building Exhibit Halls ABC 085
award Highlight
[ ] [ Project Page ]
[ Paper PDF [ Slides [ Poster

Abstract:

We propose Gated Stereo, a high-resolution and long-range depth estimation technique that operates on active gated stereo images. Using active and high dynamic range passive captures, Gated Stereo exploits multi-view cues alongside time-of-flight intensity cues from active gating. To this end, we propose a depth estimation method with a monocular and stereo depth prediction branch which are combined in a final fusion stage. Each block is supervised through a combination of supervised and gated self-supervision losses. To facilitate training and validation, we acquire a long-range synchronized gated stereo dataset for automotive scenarios. We find that the method achieves an improvement of more than 50 % MAE compared to the next best RGB stereo method, and 74 % MAE to existing monocular gated methods for distances up to 160 m. Our code, models and datasets are available here: https://light.princeton.edu/gatedstereo/.

Chat is not available.