A Learned Stereo Depth System for Robotic Manipulation in Homes
원문 초록
We present a passive stereo depth system that produces dense and accurate point clouds optimized for human environments, including dark, textureless, thin, reflective and specular surfaces and objects, at 2560x2048 resolution, with 384 disparities, in 30 ms. The system consists of an algorithm combining learned stereo matching with engineered filtering, a training and data-mixing methodology, and a sensor hardware design. Our architecture is 15x faster than approaches that perform similarly on the Middlebury and Flying Things Stereo Benchmarks. To effectively supervise the training of this model, we combine real data labelled using off-the-shelf depth sensors, as well as a number of different rendered, simulated labeled datasets. We demonstrate the efficacy of our system by presenting a large number of qualitative results in the form of depth maps and point-clouds, experiments validating the metric accuracy of our system and comparisons to other sensors on challenging objects and scenes. We also show the competitiveness of our algorithm compared to state-of-the-art learned models using the Middlebury and FlyingThings datasets.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching
Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts
Multi-Label Stereo Matching for Transparent Scene Depth Estimation
Diving into the Fusion of Monocular Priors for Generalized Stereo Matching
Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model
Distilling Stereo Networks for Performant and Efficient Leaner Networks
토론
이 논문과 연결된 포럼 글이 아직 없습니다.