Research map / Video / Video segmentation and tracking
Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method
Tianyi Liu, Kejun Wu, YI WANG, Wenyang Liu, Kim-Hui Yap, Lap-Pui Chau
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 the feature enhancement module that encodes residual content from corrupted regions | BSCVR · DAVIS (480P) Subset, original resolution | PSNR: 26.6723 -> 27.2770 | Improved |
| Train on bitstream-corrupted videos rather than use the pretrained model | E2FGVI-HQ · YouTube-VOS (720P) Subset, 240P | PSNR: 28.5039 -> 29.5666 | Improved |
| Use patch-based rather than sequence-based feature enhancement (ablation) | BSCVR · YouTube-VOS (720P) Subset, 240P | PSNR: 31.8345 -> 31.9534 | Improved |
| Use patch-based rather than sequence-based feature enhancement (ablation) | BSCVR · DAVIS (480P) Subset, original resolution | PSNR: 27.2770 -> 26.3564 | Hurt |
| Increase corruption probability from 1/16 to 2/16 | BSCV branch evaluated with BSCVR-S · DAVIS Subset, original resolution | PSNR: 27.2770 -> 24.5066 | Hurt |
| Increase corruption fragment size from 4096 to 8192 | BSCV branch evaluated with BSCVR-S · DAVIS Subset, original resolution | PSNR: 27.2770 -> 26.2708 | Hurt |
Closest papers by meaning
- Blind Bitstream-corrupted Video Recovery via Metadata-guided Diffusion Model (CVPR 2025 · similarity 0.90)
- Bitstream-Corrupted JPEG Images Are Restorable: Two-Stage Compensation and Alignment Framework for Image Restoration (CVPR 2023 · similarity 0.84)
- Reconstructing High Quality Raw Video Using Temporal Affinity and Diffusion Prior (TPAMI 2025 · similarity 0.83)
- Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models (TPAMI 2024 · similarity 0.83)
- VVS: Video-to-Video Retrieval with Irrelevant Frame Suppression (AAAI 2024 · similarity 0.82)
- LAVIB: A Large-scale Video Interpolation Benchmark (NeurIPS 2024 · similarity 0.81)
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.
