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

• URL: http://arxiv.org/abs/2603.05756v1
• Date: Thu, 05 Mar 2026 23:30:34 GMT
• Title: Uni-LVC: A Unified Method for Intra- and Inter-Mode Learned Video Compression
• Abstract summary: 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.<n>Building on a strong intra-codec, Uni-LVC formulates inter-coding as intra-coding conditioned on temporal information extracted from reference frames.<n>A reliability-aware classifier is proposed to selectively scale the temporal cues, making Uni-LVC behave closer to intra coding when references are unreliable.
• Score: 12.0699499858344
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Boosting Neural Video Codec via Scale-Driven Online Flow Refinement [59.68390983151205]
  We propose a Training-Free Scale-Driven Online Flow Refinement (SOFR) method.<n>It fuses motion information from coarse and fine scales according to warping accuracy, effectively rectifying motion estimation errors.<n>It brings an average of 2.84% and 4.05% savings in terms of PSNR and MS-SSIM, respectively.
  arXiv  Detail & Related papers  (2026-06-22T08:36:23Z)
• Ultra-Fast Neural Video Compression [29.065189275652944]
  This paper introduces a chunk-based coding framework designed to significantly improve the rate-distortion-complexity trade-off.<n>Instead of processing frames sequentially, our approach encodes a chunk of multiple frames into a single compact latent representation and decodes them simultaneously.<n>Building on these innovations, we present DCVC-UF, a new NVC that sets a new SOTA in performance.
  arXiv  Detail & Related papers  (2026-06-03T03:38:05Z)
• Real-Time Neural Video Compression with Unified Intra and Inter Coding [8.998142257336674]
  We present an NVC framework with unified intra and inter coding, where every frame is processed by a single model.<n>We propose a simultaneous two-frame compression design to exploit interframe redundancy not only forwardly but also backwardly.<n>Our scheme outperforms DCVC-RT by an average of 12.1% BD-rate reduction, delivers more stable and quality per frame, and retains real-time encoding/decoding performances.
  arXiv  Detail & Related papers  (2025-10-16T08:31:44Z)
• NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows [75.70583906344815]
  Diffusion models have been widely adopted as action decoders due to their ability to model complex, multimodal action distributions.<n>We present NinA, a fast and expressive alternative to diffusion-based decoders for Vision-Language-Action (VLA) models.
  arXiv  Detail & Related papers  (2025-08-23T00:02:15Z)
• KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding [72.12756830560217]
  Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI.<n>Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value cache during inference has emerged as a primary efficiency bottleneck.<n>By down-sampling the Key-Value vector dimensions into a latent space, we can significantly reduce the KV Cache footprint and improve inference speed.
  arXiv  Detail & Related papers  (2025-07-15T12:52:12Z)
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding [51.711605076319216]
  Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities.<n>We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.<n>We propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality.
  arXiv  Detail & Related papers  (2025-05-28T17:39:15Z)
• Towards Practical Real-Time Neural Video Compression [60.390180067626396]
  We introduce a practical real-time neural video (NVC) designed to deliver high compression ratio, low latency and broad versatility.<n>Experiments show our proposed DCVC-RT achieves an impressive average encoding/desampling speed 125.2/112.8 (frames per second) for 1080p video, while saving an average of 21% in fps compared to H.266/VTM.
  arXiv  Detail & Related papers  (2025-02-28T06:32:23Z)
• Deep Learning-Based Intra Mode Derivation for Versatile Video Coding [65.96100964146062]
  An intelligent intra mode derivation method is proposed in this paper, termed as Deep Learning based Intra Mode Derivation (DLIMD) The architecture of DLIMD is developed to adapt to different quantization parameter settings and variable coding blocks including non-square ones. The proposed method can achieve 2.28%, 1.74%, and 2.18% bit rate reduction on average for Y, U, and V components on the platform of Versatile Video Coding (VVC) test model.
  arXiv  Detail & Related papers  (2022-04-08T13:23:59Z)
• Neural Video Coding using Multiscale Motion Compensation and Spatiotemporal Context Model [45.46660511313426]
  We propose an end-to-end deep neural video coding framework (NVC) It uses variational autoencoders (VAEs) with joint spatial and temporal prior aggregation (PA) to exploit the correlations in intra-frame pixels, inter-frame motions and inter-frame compensation residuals. NVC is evaluated for the low-delay causal settings and compared with H.265/HEVC, H.264/AVC and the other learnt video compression methods.
  arXiv  Detail & Related papers  (2020-07-09T06:15:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.