Revisiting the Current Frame: Physical-Trace-Guided Network Output Correction for Video Restoration
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present ANCHOR, a new method to improve video restoration by using the current low-quality frame as a trusted reference point. Their approach helps correct errors that come from relying too much on other frames, which might have inconsistencies or occlusions. ANCHOR estimates which parts of the video are reliable and mixes the restored output with the original data accordingly. Tests on tasks like HDR video reconstruction and removing rain from videos show that ANCHOR consistently improves existing restoration models.
video restorationtemporal informationimage degradationspatial trust fieldHDR video reconstructionvideo derainingtemporal alignmentphysical image-formationadaptive correction
Authors
Yifeng Lin, Liuxiang Qiu, Guangming Ren, Tiesong Zhao
Abstract
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.