HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching
Vladimir Tankovich, Christian Hane, Yinda Zhang, Adarsh Kowdle, Sean Ryan Fanello, Sofien Bouaziz
2021Year
50Top-tier citations
Abstract
Example result of HITNet on the SceneFlow, KITTI, ETH3D and Middlebury datasets. Our approach predicts accurate depth with crisp edges. HITNet obtains state-of-art results on KITTI, ETH3D and Middlebury-v3 benchmarks.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 40b4062e-77c5-4f82-a093-76fa78e7a813Cited by top-tier papers50
- Practical Stereo Matching via Cascaded Recurrent Network with Adaptive CorrelationJiankun Li, Peisen Wang, Pengfei Xiong, Tao Cai et al.CVPR 2022 · 294 citations
- Attention Concatenation Volume for Accurate and Efficient Stereo MatchingGangwei Xu, Junda Cheng, Peng Guo, Xin YangCVPR 2022 · 265 citations
- CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical FlowPhilippe Weinzaepfel, Thomas Lucas, Vincent Leroy, Yohann Cabon et al.ICCV 2023 · 181 citations
- Total relighting: learning to relight portraits for background replacementRohit Pandey, Sergio Orts-Escolano, Chloe LeGendre, Christian Häne et al.SIGGRAPH 2021 · 138 citations
- Pseudo-Stereo for Monocular 3D Object Detection in Autonomous DrivingYi-Nan Chen, Hang Dai, Yong DingCVPR 2022 · 91 citations
Builds on2
Related papers
- Semantic Scene Completion via Integrating Instances and Scene In-the-LoopYingjie Cai, Xuesong Chen, Chao Zhang, Kwan-Yee Lin et al.CVPR 2021
- VA-DepthNet: A Variational Approach to Single Image Depth PredictionCe Liu, Suryansh Kumar, Shuhang Gu, Radu Timofte et al.ICLR 2023 · 17 citations
- Mirror3D: Depth Refinement for Mirror SurfacesJiaqi Tan, Weijie Lin, Angel X. Chang, Manolis SavvaCVPR 2021
- Stereo Risk: A Continuous Modeling Approach to Stereo MatchingCe Liu, Suryansh Kumar, Shuhang Gu, Radu Timofte et al.ICML 2024 · 8 citations
- Categorical Depth Distribution Network for Monocular 3D Object DetectionCody Reading, Ali Harakeh, Julia Chae, Steven L. WaslanderCVPR 2021
