Research map / Video / Video segmentation and tracking
Video Restoration Framework and Its Meta-Adaptations to Data-Poor Conditions
Prashant W Patil, Sunil Gupta, Santu Rana, Svetha Venkatesh
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 scale modulation to the baseline network (ablation) | Proposed video restoration network · REVIDE video de-hazing | PSNR: 22.74 -> 23.69 | Improved |
| add temporal modulation to the baseline network (ablation) | Proposed video restoration network · REVIDE video de-hazing | PSNR: 22.74 -> 23.95 | Improved |
| combine scale and temporal modulation (STFM) (ablation) | Proposed video restoration network · REVIDE video de-hazing | PSNR: 22.74 -> 24.64 | Improved |
| add multi-level feature aggregation (MFA) (ablation) | Proposed video restoration network · REVIDE video de-hazing | PSNR: 24.64 -> 25.42 | Improved |
| add previous frame output feedback to the decoder (ablation) | Proposed video restoration network · REVIDE video de-hazing | PSNR: 25.42 -> 26.36 | Improved |
| add previous frame output feedback to the decoder (ablation) | Proposed video restoration network · REVIDE video de-hazing | SSIM: 0.8814 -> 0.9044 | Improved |
| use meta-learning adaptation instead of scratch training | Proposed network · night-time de-hazing | PSNR: 21.99 -> 23.67 | Improved |
| use meta-learning adaptation instead of scratch training | Proposed network · night-time de-raining | PSNR: 23.57 -> 24.71 | Improved |
| use meta-learning adaptation instead of scratch training | Proposed network · night-time de-raining with veil | PSNR: 22.21 -> 23.49 | Improved |
| fine-tune day-time model on night data instead of scratch training | Proposed network · night-time de-raining | PSNR: 23.57 -> 22.78 | Hurt |
| fine-tune day-time model on night data instead of scratch training | Proposed network · night-time de-hazing | PSNR: 21.99 -> 22.01 | No clear effect |
| use meta-adaptation with only 10% of night training samples | Proposed network · night-time restoration tasks | PSNR/SSIM | Improved |
Closest papers by meaning
- Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal (CVPR 2024 · similarity 0.91)
- Language-driven All-in-one Adverse Weather Removal (CVPR 2024 · similarity 0.89)
- AWRaCLe: All-Weather Image Restoration Using Visual In-Context Learning (AAAI 2025 · similarity 0.89)
- Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start (NeurIPS 2025 · similarity 0.88)
- Multi-axis Prompt and Multi-dimension Fusion Network for All-in-one Weather-degraded Image Restoration (AAAI 2025 · similarity 0.88)
- End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning (NeurIPS 2024 · similarity 0.87)
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.
