Research map / 3D vision / Depth and stereo
Poppy: Polarization-Based Plug-and-Play Guidance for Enhancing Surface Normal Estimation
Irene Kim, Sai Tanmay Reddy Chakkera, Alexandros Graikos, Dimitris Samaras, Akshat Dave
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 Poppy polarization guidance | Marigold · Synthetic benchmarks | mean angular error: 20.99 -> 15.60 | Improved |
| add Poppy polarization guidance | Marigold · Real benchmarks | mean angular error: 18.18 -> 15.28 | Improved |
| add Poppy polarization guidance | Lotus-v2 · Synthetic benchmarks | mean angular error: 16.52 -> 12.26 | Improved |
| add Poppy polarization guidance | Lotus-v2 · Real benchmarks | mean angular error: 14.68 -> 12.65 | Improved |
| add Poppy polarization guidance | MoGe-2 · Synthetic benchmarks | mean angular error: 14.13 -> 10.89 | Improved |
| add Poppy polarization guidance | MoGe-2 · Real benchmarks | mean angular error: 13.10 -> 12.26 | Improved |
| add Poppy polarization guidance | MoGe-2 · Synthetic benchmarks | Acc11.25: 0.51 -> 0.70 | Improved |
| add Poppy polarization guidance | Lotus-v2 · Synthetic benchmarks | Acc11.25: 0.42 -> 0.66 | Improved |
| add Poppy polarization guidance | MoGe-2 · PISR (real) | mean angular error | Hurt |
| add normal offset on top of image offset (joint guidance) (ablation) | Poppy · Synthetic datasets | mean angular error | Improved |
| add normal offset on top of image offset (joint guidance) (ablation) | Poppy · Real datasets | mean angular error | Hurt |
| add image offset alone (ablation) | Poppy · Synthetic and real datasets | mean angular error | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MoGe-2 — MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details (NeurIPS 2025) · better on 4 of 4 shared results
- SfPUEL — SfPUEL: Shape from Polarization under Unknown Environment Light (NeurIPS 2024) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- RGB-to-Polarization Estimation: A New Task and Benchmark Study (NeurIPS 2025 · similarity 0.89)
- Rethinking Inductive Biases for Surface Normal Estimation (CVPR 2024 · similarity 0.88)
- Glossy Object Reconstruction with Cost-effective Polarized Acquisition (CVPR 2025 · similarity 0.86)
- PolarFree: Polarization-based Reflection-Free Imaging (CVPR 2025 · similarity 0.86)
- SfPUEL: Shape from Polarization under Unknown Environment Light (NeurIPS 2024 · similarity 0.86)
- Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering (NeurIPS 2024 · similarity 0.86)
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.
