# Revisiting the Current Frame: Physical-Trace-Guided Network Output Correction for Video Restoration

arXiv: https://arxiv.org/abs/2608.09342 · HTML: https://mlsanity.com/paper/2608.09342/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 23 of 23)

- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Plug-and-Play Image Restoration with Deep Denoiser Prior](https://mlsanity.com/paper/2008.13751/) (2020)
- [Denoising Diffusion Models for Plug-and-Play Image Restoration](https://mlsanity.com/paper/2305.08995/) (2023)
- [Learning A Sparse Transformer Network for Effective Image Deraining](https://mlsanity.com/paper/2303.11950/) (2023)
- [Recurrent Video Restoration Transformer with Guided Deformable Attention](https://mlsanity.com/paper/2206.02146/) (2022)
- [Attention-guided Network for Ghost-free High Dynamic Range Imaging](https://mlsanity.com/paper/1904.10293/) (2019)
- [RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining](https://mlsanity.com/paper/2407.21773/) (2024)
- [Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework](https://mlsanity.com/paper/1803.10433/) (2018)
- [HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset](https://mlsanity.com/paper/2103.14943/) (2021)
- [Enhanced Spatio-Temporal Interaction Learning for Video Deraining: A Faster and Better Framework](https://mlsanity.com/paper/2103.12318/) (2021)
- [Blind Video Deflickering by Neural Filtering with a Flawed Atlas](https://mlsanity.com/paper/2303.08120/) (2023)
- [LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction](https://mlsanity.com/paper/2308.11116/) (2023)
- [Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization](https://mlsanity.com/paper/2410.07901/) (2024)
- [Exposure Completing for Temporally Consistent Neural High Dynamic Range Video Rendering](https://mlsanity.com/paper/2407.13309/) (2024)
- [Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video](https://mlsanity.com/paper/2412.11395/) (2024)
- [Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance](https://mlsanity.com/paper/2405.09996/) (2024)
- [Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining](https://mlsanity.com/paper/2505.16811/) (2025)
- [Neural Super-Resolution for Real-time Rendering with Radiance Demodulation](https://mlsanity.com/paper/2308.06699/) (2023)
- [DeLiVR: Differential Spatiotemporal Lie Bias for Efficient Video Deraining](https://mlsanity.com/paper/2509.21719/) (2025)
- [Task Agnostic Restoration of Natural Video Dynamics](https://mlsanity.com/paper/2206.03753/) (2022)
- [Beyond the Ground Truth: Enhanced Supervision for Image Restoration](https://mlsanity.com/paper/2512.03932/) (2025)
- [F2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling](https://mlsanity.com/paper/2603.14920/) (2026)

## Abstract (arXiv)

Video restoration methods exploit temporal information to recover information missing from degraded observations. However, reference frames within the sequence may introduce inconsistent degradation, content discrepancy, or reconstruction errors due to physical image-formation variations, occlusion, and imperfect temporal aggregation. Existing approaches mainly focus on improving restoration networks, while the reliability of the generated outputs at different spatial locations remains largely unexplored. In this work, we propose ANCHOR, a model-agnostic framework that revisits the low-quality current frame as a temporally aligned anchor for video restoration correction. Specifically, ANCHOR estimates a spatial trust field from heterogeneous physical-trace evidence and adaptively balances the restoration proposal with the original observation. Experiments on High Dynamic Range video reconstruction and video deraining demonstrate consistent improvements across various state-of-the-art restoration models, validating the effectiveness of reliability-aware output correction for video restoration.