Research map / 3D vision / Depth and stereo
Light Field Reconstruction Using Shearlet Transform
Suren Vagharshakyan, Robert Bregović, Atanas P. Gotchev
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 |
|---|---|---|---|
| use the proposed EPI shearlet instead of Haar wavelet | EPI reconstruction · Synthetic EPI | PSNR (dB): 24 dB -> 41.57 dB | Improved |
| use proposed shearlet instead of shearlab | EPI reconstruction · Synthetic EPI | PSNR (dB): 33 dB -> 41.57 dB | Improved |
| use proposed shearlet instead of FFST | EPI reconstruction · Synthetic EPI | PSNR (dB): 39.65 dB -> 41.57 dB | Improved |
| use 25 views with proposed instead of SFFT with 93 views | light field reconstruction · Truck | PSNR (dB): 36.4 dB -> 40.6 dB | Improved |
| use 25 views with proposed instead of SFFT with 93 views | light field reconstruction · Bunny | PSNR (dB): 38.8 dB -> 37.8 dB | Hurt |
| increase input views from 5x5 to 9x9 (ablation) | proposed shearlet reconstruction · Bunny | PSNR (dB): 37.8 dB -> 38.9 dB | Improved |
| increase input views from 5x5 to 9x9 (ablation) | proposed shearlet reconstruction · Truck | PSNR (dB): 40.6 dB -> 41.2 dB | Improved |
| use proposed method instead of depth-layering IBR | view reconstruction · Teddy | PSNR (dB): 33.25 dB -> 33.33 dB | No clear effect |
| use iteration-adaptive acceleration parameter instead of fixed alpha (ablation) | iterative shearlet reconstruction · convergence | PSNR (dB): alpha=20 diverges | Improved |
Closest papers by meaning
- Sheared Epipolar Focus Spectrum for Dense Light Field Reconstruction (TPAMI 2023 · similarity 0.88)
- What Sparse Light Field Coding Reveals About Scene Structure (CVPR 2016 · similarity 0.87)
- Diving Into Epipolar Transformers for Light Field Super-Resolution and Disparity Estimation (TPAMI 2026 · similarity 0.87)
- Heterogeneous Light Fields (CVPR 2016 · similarity 0.86)
- TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light (CVPR 2024 · similarity 0.84)
- 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes (CVPR 2025 · similarity 0.84)
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.
