Research map / Image generation / Super-resolution
Learning Light Field Angular Super-Resolution via a Geometry-Aware Network
Read the paperCheck 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 geometry-aware depth estimation, warping, and light field blending | Angular super-resolution from four corner views to a 7×7 light field · HCI, HCI old, and Inria DLFD | PSNR: 34.60 vs 32.30; 40.84 vs 39.69; 34.83 vs 32.53 | Helped |
| Use light field blending instead of view blending (ablation) | The proposed depth-estimation and warping pipeline · HCI | PSNR: 32.69 -> 34.29 | Helped |
| Use light field blending instead of view blending (ablation) | The proposed depth-estimation and warping pipeline · HCI old | PSNR: 39.25 -> 40.70 | Helped |
| Use light field blending instead of view blending (ablation) | The proposed depth-estimation and warping pipeline · Inria DLFD | PSNR: 33.17 -> 34.56 | Helped |
| Add the EPI gradient loss (ablation) | The proposed geometry-aware network · Light field angular super-resolution | parallax structure preservation | Helped |
| Use depth estimation and physically based warping to synthesize novel views (ablation) | The proposed geometry-aware network · Large-baseline light field reconstruction | reconstruction quality | Helped |
Closest papers by meaning
- Light Field Spatial Super-Resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization (CVPR 2020 · similarity 0.92)
- Residual Networks for Light Field Image Super-Resolution (CVPR 2019 · similarity 0.92)
- NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis (CVPR 2024 · similarity 0.88)
- Occlusion-Embedded Hybrid Transformer for Light Field Super-Resolution (AAAI 2025 · similarity 0.87)
- From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy (NeurIPS 2025 · similarity 0.86)
- Time-Efficient Light-Field Acquisition Using Coded Aperture and Events (CVPR 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.