# LoopMoEVR: Loop-Based Degradation-Aware Mixture-of-Experts for Unified UHD Video Restoration

arXiv: https://arxiv.org/abs/2610.05109 · HTML: https://mlsanity.com/paper/2610.05109/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 27 of its 33 references that are in the map.
- First posted on arXiv 4 Oct 2026.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://mlsanity.com/paper/2502.05171/) (2025)
- [Reasoning with Latent Thoughts: On the Power of Looped Transformers](https://mlsanity.com/paper/2502.17416/) (2025)
- [Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation](https://mlsanity.com/paper/2507.10524/) (2025)
- [AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation](https://mlsanity.com/paper/2403.14614/) (2024)
- [Complexity Experts are Task-Discriminative Learners for Any Image Restoration](https://mlsanity.com/paper/2411.18466/) (2024)
- [LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation](https://mlsanity.com/paper/2602.11451/) (2026)
- [On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding](https://mlsanity.com/paper/2410.01405/) (2024)
- [SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers](https://mlsanity.com/paper/2609.01343/) (2026)
- [UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity](https://mlsanity.com/paper/2412.20157/) (2024)
- [ELT: Elastic Looped Transformers for Visual Generation](https://mlsanity.com/paper/2604.09168/) (2026)
- [Always Clear Days: Degradation Type and Severity Aware All-In-One Adverse Weather Removal](https://mlsanity.com/paper/2310.18293/) (2023)
- [LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language Modeling](https://mlsanity.com/paper/2606.04438/) (2026)
- [Cross-Consistent Deep Unfolding Network for Adaptive All-In-One Video Restoration](https://mlsanity.com/paper/2309.01627/) (2023)
- [UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration](https://mlsanity.com/paper/2507.23685/) (2025)
- [Grounding Degradations in Natural Language for All-In-One Video Restoration](https://mlsanity.com/paper/2507.14851/) (2025)
- [Looped World Models](https://mlsanity.com/paper/2606.18208/) (2026)
- [All-in-One Video Restoration under Smoothly Evolving Unknown Weather Degradations](https://mlsanity.com/paper/2601.00533/) (2026)
- [Removing Multiple Hybrid Adverse Weather in Video via a Unified Model](https://mlsanity.com/paper/2503.06200/) (2025)
- [LaverNet: Lightweight All-in-one Video Restoration via Selective Propagation](https://mlsanity.com/paper/2512.16313/) (2025)
- [MoCRA: Mixture of Compositional Rank-1 Atoms for 4K All-in-One Video Restoration](https://mlsanity.com/paper/2608.01829/) (2026)

## Abstract (arXiv)

Recently, unified high-definition image restoration has attracted considerable attention; however, existing models tend to excessively increase their depth in pursuit of improved generalization, which often yields only limited gains. Meanwhile, loop-based learning paradigms have drawn widespread attention due to their low parameter counts and strong regression capability, as exemplified by GPT-6 and looped Transformers. In this paper, we introduce the loop learning paradigm to address restoration tasks that require cross-domain learning. Specifically, we propose LoopMoEVR, a loop-based mixture-of-experts model capable of handling degraded ultra-high-definition (UHD) inputs. First, a degradation-conditioned low-rank loop embedding is designed to construct input-dependent stage conditions. Second, a spatio-temporal iterative adaptive normalization module, termed IterAda3DN, is developed to fuse local features with global loop context, thereby performing position-wise affine modulation. Finally, the expert branches further integrate the attention-updated local and global video states with the loop conditions to generate dedicated modulation parameters, while an input-conditioned depth predictor adaptively configures the number of loop iterations. With only approximately 0.884M trainable parameters, the proposed model uniformly handles UHD video dehazing, deraining, denoising, and low-light enhancement tasks, achieving state-of-the-art restoration performance on both public benchmarks and real-world scenarios.