Uni-LVC: A Unified Method for Intra- and Inter-Mode Learned Video Compression

TL;DR

Uni-LVC is a unified learned video compression method that effectively supports intra and inter coding modes within a single model, improving performance and robustness across different video coding scenarios.

Contribution

It introduces a novel unified framework with a cross-attention module and reliability-aware classifier, enabling seamless intra and inter coding in learned video compression.

Findings

Achieves superior rate-distortion performance in intra and inter modes.

Maintains computational efficiency comparable to existing methods.

Demonstrates robustness when temporal references are unreliable.

Abstract

Recent advances in learned video compression (LVC) have led to significant performance gains, with codecs such as DCVC-RT surpassing the H.266/VVC low-delay mode in compression efficiency. However, existing LVCs still exhibit key limitations: they often require separate models for intra and inter coding modes, and their performance degrades when temporal references are unreliable. To address this, we introduce Uni-LVC, a unified LVC method that supports both intra and inter coding with low-delay and random-access in a single model. Building on a strong intra-codec, Uni-LVC formulates inter-coding as intra-coding conditioned on temporal information extracted from reference frames. We design an efficient cross-attention adaptation module that integrates temporal cues, enabling seamless support for both unidirectional (low-delay) and bidirectional (random-access) prediction modes. A reliability-aware classifier is proposed to selectively scale the temporal cues, making Uni-LVC behave closer to intra coding when references are unreliable. We further propose a multistage training strategy to facilitate adaptive learning across various coding modes. Extensive experiments demonstrate that Uni-LVC achieves superior rate-distortion performance in intra and inter configurations while maintaining comparable computational efficiency.