cs.CVNov 17, 2026

Fast Training-Free Low-Light Video Enhancement with a Frozen Image Diffusion Prior

Authors: Hon Ming Yam, Chun Pong Lau

Organizations: City University of Hong Kong

Abstract

Pretrained image diffusion models can enhance low-light video without low-light training data and without retraining for a new camera. ZVRD, the only published training-free method for low-light video, is too slow to use: our implementation needs over a minute per 256×256256 \times 256 frame. We present a causal, training-free pipeline that adds two temporal components to a frozen MR. Illuminate image prior. Temporal input fusion recursively averages motion-compensated low-light frames before diffusion inversion. Late-start offset propagation runs the full sampling trajectory only on key frames. Each non-key frame inverts the low-noise part of its own trajectory and adds an enhancement offset warped from the latest key frame. At ZVRD's own resolution the pipeline is 261×261\times faster than ZVRD and scores better on all five metrics we report. On 13 held-out SDSD clips at 1280×7201280 \times 720, it improves on framewise eight-step processing by 0.55 dB in PSNR and 0.034 in LPIPS and halves the warping error, in 10% less time. Measurements inside the model show why, and a linear-Gaussian model of inversion explains them. Fusion removes frame-to-frame noise before inversion amplifies it. A flow error perturbs the transported offset ten times less than it perturbs a transported state. The perceptual gain does not transfer to low resolution: at 346×260346 \times 260, LPIPS is worse by 0.028. At 0.65 frames per second, the pipeline is an offline method.

Figures & tables

Explore similar work

CardsList
  1. InstantViR: Real-Time Video Inverse Problem Solver with Distilled Diffusion Prior

    Nov 18, 2025Weimin Bai, Suzhe Xu, Yiwei Ren +4Diffusion-Based Inverse ProblemsVideo Diffusion Models

  2. LiteVSR: Lightweight Adaptation of Frozen Diffusion Transformers for Video Super-Resolution

    Jun 8, 2026Yu Cao, Ziquan Liu, Zhensong Zhang +3Video Diffusion ModelsDiffusion Transformer