Research map / 3D vision / Depth and stereo
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation
Peng Li, Jiayin Zhao, Jingyao Wu, Chao Deng, Yuqi Han, Haoqian Wang, Tao Yu
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 OPAL occlusion-pattern loss (ablation) | OPENet-fast · 4D LF Benchmark (4-scene average, ablation) | MSE x100: 3.828 -> 1.978 | Improved |
| simplify occlusion patterns with beta=4 instead of beta=1 (ablation) | OPENet-fast · 4D LF Benchmark (4-scene average, ablation) | MSE x100: 1.978 -> 1.908 | Improved |
| use non-simplified patterns beta=1 instead of beta=4 (ablation) | OPENet-fast · 4D LF Benchmark (Sideboard) | MSE x100: 1.141 -> 1.000 | Improved |
| add refinement module (ablation) | OPENet · 4D LF Benchmark (4-scene average, ablation) | MSE x100: 1.820 -> 1.672 | Improved |
| add EPI-Transformer (ablation) | OPENet · 4D LF Benchmark (4-scene average, ablation) | MSE x100: 1.808 -> 1.672 | Improved |
| add raw-disparity loss term (ablation) | OPENet · 4D LF Benchmark (4-scene average, ablation) | MSE x100: 1.755 -> 1.672 | Improved |
| add smoothness loss (ablation) | OPENet · 4D LF Benchmark (4-scene average, ablation) | MSE x100: 2.482 -> 1.672 | Improved |
| use unsupervised OPENet instead of supervised LFattNet across datasets | OPENet · 4D LF Benchmark + HCI Blender (cross-dataset average) | MSE x100: 2.164 -> 1.127 | Improved |
| use OPENet instead of OPENet-fast (EPI-Transformer, refinement, four directions) | OPENet · 4D LF Benchmark + HCI Blender (cross-dataset average) | MSE x100: 1.315 -> 1.127 | Improved |
Closest papers by meaning
- Take Your Model Further: A General Post-refinement Network for Light Field Disparity Estimation via BadPix Correction (AAAI 2023 · similarity 0.87)
- A Novel Occlusion-aware Vote Cost for Light Field Depth Estimation (TPAMI 2021 · similarity 0.87)
- Trust Your Model: Light Field Depth Estimation With Inline Occlusion Handling (CVPR 2018 · similarity 0.87)
- Fast Light-Field Disparity Estimation With Multi-Disparity-Scale Cost Aggregation (ICCV 2021 · similarity 0.87)
- Depth Estimation with Occlusion Modeling Using Light-Field Cameras (TPAMI 2016 · similarity 0.87)
- Robust Light Field Depth Estimation Using Occlusion-Noise Aware Data Costs (TPAMI 2017 · 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.
