LoopMoEVR: Loop-Based Degradation-Aware Mixture-of-Experts for Unified UHD Video Restoration
cs.CV
Submitted: 2026-10-04
Updated: 2026-10-04
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language Modeling
- Cross-Consistent Deep Unfolding Network for Adaptive All-In-One Video Restoration
- Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
- All-in-One Video Restoration under Smoothly Evolving Unknown Weather Degradations
- Looped World Models
- SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
- MoCRA: Mixture of Compositional Rank-1 Atoms for 4K All-in-One Video Restoration
- LaverNet: Lightweight All-in-one Video Restoration via Selective Propagation
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