cs.CVNov 4, 2026

Perceptual Distortion for Overfitted Video Coding: Sliced Matching in Space, Error Alignment in Time

Authors: Tianyi Yang, Ge Gao, Fan Zhang, David Bull

Organizations: Visual Information Laboratory, University of Bristol, Bristol, UK

Abstract

Recent works in neural video coding have increasingly been trading off perceptual quality against reconstruction fidelity at a fixed bitrate. Wasserstein Distortion (WD) offers a principled approach to balancing these objectives by relaxing spatial correspondences in feature matching, enabling lightweight overfitted image codecs to compete with computationally intensive generative decoders. Extending vanilla WD to video, however, presents two challenges: its independent Gaussian approximation limits the expressiveness of feature distribution matching, while unconstrained texture resampling across frames introduces temporal inconsistencies. We address these challenges by distinguishing between the correspondences that can be relaxed and those that must be preserved. Spatially, we introduce a local sliced Wasserstein distortion (SWD) that matches empirical feature distributions through one-dimensional optimal transport, capturing cross-channel dependencies without enforcing exact spatial alignment. Temporally, we employ a novel flow residual that constrains coding errors along motion trajectories, preserving temporal consistency without imposing additional reconstruction fidelity constraints. Evaluated on UVG and HEVC Class B with the overfitted codec COOL-CHIC, our framework achieves BD-rate reductions of 9.2% in DISTS and 3.0% in LPIPS relative to frame-wise WD, averaged over test sequences, while lowering tOF by 10.2% at matched rate.

Figures & tables

Explore similar work

CardsList
  1. Boosting Neural Video Codec via Scale-Driven Online Flow Refinement

    Jun 22, 2026Tiange Zhang, Rongqun Lin, Haocheng Tang +4Optical FlowMulti-Scale Feature Fusion

  2. Neural Video Compression Based on Deformable Temporal Alignment and Difference-aware Fusion

    Sep 3, 2026Chuyue Shan, Songlin Sun, Wang Chenwei +1Neural Video Compression

  3. NeuralLVC: Neural Lossless Video Compression via Masked Diffusion with Temporal Conditioning

    Apr 3, 2026Tiberio Uricchio, Marco BertiniMasked Diffusion ModelsNeural Video Compression