Research map / 3D vision / Depth and stereo
Convolutional Networks for Shape From Light Field
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 variational refinement to the CNN prediction (ablation) | CNN hyperplane prediction · POV-Ray test set, average | RMSE (×100): 0.3227 -> 0.3010 | Helped |
| Add variational refinement to the CNN prediction (ablation) | CNN hyperplane prediction · POV-Ray test set, scene 1 | RMSE (×100): 0.2593 -> 0.2575 | Hurt |
| Add variational refinement to the CNN prediction (ablation) | CNN hyperplane prediction · POV-Ray test set, scene 2 | RMSE (×100): 0.5577 -> 0.5202 | Helped |
| Add variational refinement to the CNN prediction (ablation) | CNN hyperplane prediction · POV-Ray test set, scene 3 | RMSE (×100): 0.2027 -> 0.1847 | Helped |
| Add variational refinement to the CNN prediction (ablation) | CNN hyperplane prediction · POV-Ray test set, scene 4 | RMSE (×100): 0.1829 -> 0.1408 | Helped |
| Add variational refinement to the CNN prediction (ablation) | CNN hyperplane prediction · POV-Ray test set, scene 5 | RMSE (×100): 0.4110 -> 0.4018 | Helped |
| Use the proposed method instead of Heber and Pock [16] | Shape-from-light-field reconstruction · POV-Ray test set, average | RMSE (×100): 0.3774 -> 0.3010 | Helped |
| Use the proposed method instead of Wanner and Goldluecke [30] | Shape-from-light-field reconstruction · POV-Ray test set, average | RMSE (×100): 0.9168 -> 0.3010 | Helped |
| Use the proposed method instead of Heber and Pock [16] | Shape-from-light-field reconstruction · POV-Ray test set, scene 1 | RMSE (×100): 0.2501 -> 0.2575 | Hurt |
Closest papers by meaning
- EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth From Light Field Images (CVPR 2018 · similarity 0.89)
- Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering (NeurIPS 2021 · similarity 0.88)
- Attention-Based View Selection Networks for Light-Field Disparity Estimation (AAAI 2020 · similarity 0.87)
- Towards Multimodal Depth Estimation From Light Fields (CVPR 2022 · similarity 0.87)
- Light Field Intrinsics With a Deep Encoder-Decoder Network (CVPR 2018 · similarity 0.87)
- Occlusion-Aware Cost Constructor for Light Field Depth Estimation (CVPR 2022 · 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.