Research map / 3D vision / Depth and stereo
What Sparse Light Field Coding Reveals About Scene Structure
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 |
|---|---|---|---|
| Use sparse light-field coding with disparity-specific lifted atoms instead of the best listed baseline | Proposed depth estimator · HCI light field benchmark | MSE: 1.04 -> 1.11 | Mixed |
| Use the proposed estimator rather than the best listed baseline | Proposed depth estimator · buddha | MSE: 0.90 -> 0.57 | Helped |
| Use the proposed estimator rather than the best listed baseline | Proposed depth estimator · buddha2 | MSE: 0.68 -> 1.08 | Hurt |
| Use the proposed estimator rather than the best listed baseline | Proposed depth estimator · horses | MSE: 1.00 -> 3.26 | Hurt |
| Use the proposed estimator rather than the best listed baseline | Proposed depth estimator · medieval | MSE: 0.76 -> 0.84 | Hurt |
| Use the proposed estimator rather than the best listed baseline | Proposed depth estimator · monasRoom | MSE: 0.79 -> 0.65 | Helped |
| Use the proposed estimator rather than the best listed baseline | Proposed depth estimator · papillon | MSE: 3.65 -> 1.85 | Helped |
| Use the proposed estimator rather than the best listed baseline | Proposed depth estimator · stillLife | MSE: 4.23 -> 2.95 | Helped |
| Use the proposed estimator rather than the best listed baseline | Proposed depth estimator · couple | MSE: 0.30 -> 0.42 | Hurt |
| Use the proposed estimator rather than the best listed baseline | Proposed depth estimator · cube | MSE: 0.51 -> 0.51 | No clear effect |
| Use the proposed estimator rather than the best listed baseline | Proposed depth estimator · maria | MSE: 0.10 -> 0.11 | Hurt |
| Use the proposed estimator rather than the best listed baseline | Proposed depth estimator · pyramide | MSE: 0.38 -> 0.48 | Hurt |
Closest papers by meaning
- Towards Multimodal Depth Estimation From Light Fields (CVPR 2022 · similarity 0.89)
- Heterogeneous Light Fields (CVPR 2016 · similarity 0.89)
- Light Field Intrinsics With a Deep Encoder-Decoder Network (CVPR 2018 · similarity 0.89)
- EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth From Light Field Images (CVPR 2018 · similarity 0.88)
- Light Field Reconstruction Using Deep Convolutional Network on EPI (CVPR 2017 · similarity 0.88)
- NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis (CVPR 2024 · similarity 0.85)
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.