Research map / Video / Video segmentation and tracking
Synthesizing Light Field Video from Monocular Video
Shrisudhan Govindarajan, Prasan Shedligeri, Sarah, Kaushik Mitra
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 |
|---|---|---|---|
| add disocclusion handling loss (ablation) | monocular LF video model · Average over 4 LF datasets | PSNR: 29.32 -> 30.25 | Improved |
| add disocclusion handling loss (ablation) | monocular LF video model · Average over 4 LF datasets | SSIM: 0.943 -> 0.945 | Improved |
| add adaptive TD layer (ablation) | monocular LF video model · Average over 4 LF datasets | PSNR: 30.25 -> 31.09 | Improved |
| add adaptive TD layer (ablation) | monocular LF video model · Average over 4 LF datasets | SSIM: 0.945 -> 0.949 | Improved |
| add supervised refinement block (ablation) | monocular LF video model · Average over 4 LF datasets | PSNR: 31.09 -> 31.47 | Improved |
| add supervised refinement block (ablation) | monocular LF video model · Average over 4 LF datasets | SSIM: 0.949 -> 0.951 | Improved |
| add supervised refinement block (ablation) | monocular LF video model · TAMULF | PSNR: 27.42 -> 27.24 | Mixed |
| add temporal frames (video input vs image-only) (ablation) | monocular LF video model · Average over 4 LF datasets | PSNR: 31.30 -> 31.47 | Improved |
| use video-based self-supervised model vs best single-image baseline | monocular LF video model · Average over 4 LF datasets | PSNR: 29.66 -> 31.47 | Improved |
Closest papers by meaning
- SeLFVi: Self-Supervised Light-Field Video Reconstruction From Stereo Video (ICCV 2021 · similarity 0.94)
- Learning Dynamic Interpolation for Extremely Sparse Light Fields With Wide Baselines (ICCV 2021 · similarity 0.89)
- Disentangling Light Fields for Super-Resolution and Disparity Estimation (TPAMI 2022 · similarity 0.88)
- $L^{2}DGS$: Low-Light Dynamic Gaussian Splatting (CVPR 2026 · similarity 0.88)
- S2D-LFE: Sparse-to-Dense Light Field Event Generation (CVPR 2025 · similarity 0.87)
- From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy (NeurIPS 2025 · 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.
