AI Paper Atlas

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

NeurIPS 2023 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add the feature enhancement module that encodes residual content from corrupted regionsBSCVR · DAVIS (480P) Subset, original resolutionPSNR: 26.6723 -> 27.2770Improved
Train on bitstream-corrupted videos rather than use the pretrained modelE2FGVI-HQ · YouTube-VOS (720P) Subset, 240PPSNR: 28.5039 -> 29.5666Improved
Use patch-based rather than sequence-based feature enhancement (ablation)BSCVR · YouTube-VOS (720P) Subset, 240PPSNR: 31.8345 -> 31.9534Improved
Use patch-based rather than sequence-based feature enhancement (ablation)BSCVR · DAVIS (480P) Subset, original resolutionPSNR: 27.2770 -> 26.3564Hurt
Increase corruption probability from 1/16 to 2/16BSCV branch evaluated with BSCVR-S · DAVIS Subset, original resolutionPSNR: 27.2770 -> 24.5066Hurt
Increase corruption fragment size from 4096 to 8192BSCV branch evaluated with BSCVR-S · DAVIS Subset, original resolutionPSNR: 27.2770 -> 26.2708Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy