Reference-Efficient Multimodal Bitstream-Corrupted Video Recovery via Depth-Conditioned Adaptation
cs.CV
Submitted: 2026-10-11
Updated: 2026-10-14
Project page: https://intelpro.github.io/UEVD
Terminology
Sources
- Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method
- Towards Blind Bitstream-corrupted Video Recovery via a Visual Foundation Model-driven Framework
- FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting
- ProPainter: Improving Propagation and Transformer for Video Inpainting
- Blind Bitstream-corrupted Video Recovery via Metadata-guided Diffusion Model
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
- Depth Anything V2
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models