Learning To Recover 3D Scene Shape From a Single Image
Wei Yin, Jianming Zhang, Oliver Wang, Simon Niklaus, Long Mai, Simon Chen, Chunhua Shen
Abstract
Figure 1 : 3D scene structure distortion of projected point clouds. While the predicted depth map is correct, the 3D scene shape of the point cloud suffers from noticeable distortions due to an unknown depth shift and focal length (third column). Our method recovers these parameters using 3D point cloud networks. With recovered depth shift, the walls and bed edges become straight, but the overall scene is stretched (fourth column). Finally, with recovered focal length, an accurate 3D scene can be reconstructed (fifth column).
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.
Cited by top-tier papers96
- Depth Anything V2Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao et al.NeurIPS 2024 · 2,305 citations
- MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface ReconstructionZehao Yu, Songyou Peng, Michael Niemeyer, Torsten Sattler et al.NeurIPS 2022 · 670 citations
- Metric3D: Towards Zero-shot Metric 3D Prediction from A Single ImageWei Yin, Chi Zhang, Hao Chen, Zhipeng Cai et al.ICCV 2023 · 388 citations
- MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp DetailsRuicheng Wang, Sicheng Xu, Yue Dong, Yu Deng et al.NeurIPS 2025 · 308 citations
- DUSt3R: Geometric 3D Vision Made EasyShuzhe Wang, Vincent Leroy, Yohann Cabon, Boris Chidlovskii et al.CVPR 2024 · 302 citations
Builds on7
- PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationShunsuke Saito, Zeng Huang, Ryota Natsume, Shigeo Morishima et al.ICCV 2019 · 1,411 citations
- Enforcing Geometric Constraints of Virtual Normal for Depth PredictionWei Yin, Yifan Liu, Chunhua Shen, Youliang YanICCV 2019 · 487 citations
- Task-Aware Monocular Depth Estimation for 3D Object DetectionXinlong Wang, Wei Yin, Tao Kong, Yuning Jiang et al.AAAI 2020 · 63 citations
- SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth EstimationLijun Wang, Jianming Zhang, Oliver Wang, Zhe Lin et al.CVPR 2020
- OASIS: A Large-Scale Dataset for Single Image 3D in the WildWeifeng Chen, Shengyi Qian, David Fan, Noriyuki Kojima et al.CVPR 2020
Related papers
- Self-Supervised Learning of Depth Inference for Multi-View StereoJiayu Yang, José M. Álvarez, Miaomiao LiuCVPR 2021
- Cost Volume Pyramid Based Depth Inference for Multi-View StereoJiayu Yang, Wei Mao, José M. Álvarez, Miaomiao LiuCVPR 2020
- VisFusion: Visibility-Aware Online 3D Scene Reconstruction from VideosHuiyu Gao, Wei Mao, Miaomiao LiuCVPR 2023
- GP2C: Geometric Projection Parameter Consensus for Joint 3D Pose and Focal Length Estimation in the WildAlexander Grabner, Peter M. Roth, Vincent LepetitICCV 2019 · 21 citations
- HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo MatchingVladimir Tankovich, Christian Hane, Yinda Zhang, Adarsh Kowdle et al.CVPR 2021
