Research map / 3D vision / Depth and stereo
Learning Accurate 3D Shape Based on Stereo Polarimetric Imaging
Tianyu Huang, Haoang Li, Kejing He, Congying Sui, Bin Li, Yun-Hui Liu
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 |
|---|---|---|---|
| combine stereo polarization with deep learning for joint normal and disparity estimation | SfP · Our testing set | mean angular error (deg.): 22.27 -> 13.22 | Improved |
| combine stereo polarization with deep learning for joint normal and disparity estimation | SfP · Our testing set | mean disparity error (pix.): 3.91 -> 2.11 | Improved |
| add both SCMP modules for coarse-to-fine feature refinement (ablation) | stereo SfP network · Our testing set | mean angular error (deg.): 22.13 -> 13.22 | Improved |
| add the first SCMP module (ablation) | stereo SfP network without first SCMP · Our testing set | mean angular error (deg.): 16.21 -> 13.22 | Improved |
| add the second SCMP module (ablation) | stereo SfP network without second SCMP · Our testing set | mean angular error (deg.): 15.23 -> 13.22 | Improved |
| use AoLP&DoLP and Stokes maps together as inputs (ablation) | stereo SfP network · Our testing set | mean angular error (deg.): 16.51 -> 13.22 | Improved |
| use VDPE instead of APE positional encoding (ablation) | stereo SfP network · Our testing set | mean angular error (deg.): 17.68 -> 13.22 | Improved |
| use VDPE instead of RPE positional encoding (ablation) | stereo SfP network · Our testing set | mean angular error (deg.): 16.43 -> 13.22 | Improved |
| use VDPE instead of VE (ablation) | stereo SfP network · Our testing set | mean angular error (deg.): 15.89 -> 13.22 | Improved |
| use stereo polarization information | SfP normal recovery · different illumination conditions | mean variance of angular errors | Improved |
Closest papers by meaning
- Shape From Polarization for Complex Scenes in the Wild (CVPR 2022 · similarity 0.91)
- Shape from Polarization with Distant Lighting Estimation (TPAMI 2023 · similarity 0.90)
- A Differential Approach to Shape from Polarisation: A Level-Set Characterisation (IJCV 2018 · similarity 0.90)
- SfPUEL: Shape from Polarization under Unknown Environment Light (NeurIPS 2024 · similarity 0.89)
- GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors (ICLR 2024 · similarity 0.87)
- High-Fidelity Polarimetric Implicit 3D Reconstruction with View-Dependent Physical Representation (AAAI 2025 · similarity 0.87)
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.
