Research map / 3D vision / Depth and stereo
Acquiring a Dynamic Light Field Through a Single-Shot Coded Image
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 |
|---|---|---|---|
| Combine aperture coding with pixel-wise exposure coding (ablation) | Dynamic light-field acquisition from one coded image · Planets | PSNR | Helped |
| Use aperture coding without pixel-wise exposure coding (ablation) | Dynamic light-field acquisition · Planets | PSNR | Hurt |
| Use pixel-wise exposure coding without aperture coding (ablation) | Dynamic light-field acquisition · Planets | PSNR | Hurt |
| Remove both aperture and pixel-wise exposure coding (ablation) | Dynamic light-field acquisition · Planets | PSNR | Hurt |
| Use fully trainable free-form 5-D coding (ablation) | Dynamic light-field acquisition · Planets | PSNR | Helped |
| Combine aperture and pixel-wise exposure coding (ablation) | Dynamic light-field acquisition · Primitive plane scene across motion and disparity | PSNR | Helped |
| Apply pixel-wise exposure coding alone (ablation) | Dynamic light-field acquisition · Primitive plane scene with nonzero disparity | PSNR | Hurt |
| Apply aperture coding alone or no coding (ablation) | Dynamic light-field acquisition · Primitive plane scene | PSNR | Hurt |
| Increase motion velocity or disparity | A+P · Primitive plane scene | PSNR | Hurt |
| Use the proposed jointly coded acquisition rather than the compared alternatives | Dynamic light-field reconstruction · Planets | PSNR | Helped |
| Reconstruct from three consecutive images and output the central time frame | Sakai et al. · Planets with fast scene motion | PSNR | Hurt |
Closest papers by meaning
- Time-Efficient Light-Field Acquisition Using Coded Aperture and Events (CVPR 2024 · similarity 0.90)
- Real-time Acquisition and Reconstruction of Dynamic Volumes with Neural Structured Illumination (CVPR 2024 · similarity 0.87)
- Event Fields: Capturing Light Fields at High Speed, Resolution, and Dynamic Range (CVPR 2025 · similarity 0.85)
- Gated Fields: Learning Scene Reconstruction from Gated Videos (CVPR 2024 · similarity 0.85)
- SCINeRF: Neural Radiance Fields from a Snapshot Compressive Image (CVPR 2024 · similarity 0.85)
- TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light (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.