Research map / 3D vision / Depth and stereo
Simultaneous 3D Reconstruction for Water Surface and Underwater Scene
Yiming Qian, Yinqiang Zheng, Minglun Gong, Yee-Hong Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add polynomial smoothness term with lambda=2 (vs lambda=0) (ablation) | normal-consistency reconstruction · Synthetic Dragon scene | all error metrics | Improved |
| increase the number of cameras (ablation) | multi-view water surface reconstruction · Synthetic scene | error measures (Fig. 5) | Improved |
| enforce normal consistency between Snell and Quadratic normals | multi-view water surface reconstruction · Synthetic Bunny and Dragon | MAD of normals: 0.76 and 0.77; 0.36 and 0.37 | Improved |
Closest papers by meaning
- In-the-Wild Single Camera 3D Reconstruction Through Moving Water Surfaces (ICCV 2021 · similarity 0.92)
- Surface Normals and Shape From Water (ICCV 2019 · similarity 0.91)
- Non-Rigid Shape From Water (TPAMI 2021 · similarity 0.91)
- Refractive Two-View Reconstruction for Underwater 3D Vision (IJCV 2019 · similarity 0.89)
- Plenodium: Underwater 3D Scene Reconstruction with Plenoptic Medium Representation (NeurIPS 2025 · similarity 0.85)
- Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion (CVPR 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
