MLVC: Multi-platform Learned Video Codec for Real-World Deployment

Papers with Code Trending Papers
learned-video-codec neural-video-codec cross-platform video-compression real-time-inference quantization

Summary

MLVC is a hardware-robust neural video codec designed for practical cross-platform deployment. It surpasses hardware HEVC by over 70% BD-rate (MOS) on video conferencing while running at 100 FPS on commodity NPUs from Apple, Intel, and Qualcomm.

Neural video codecs have surpassed classical codecs in coding efficiency but remain impractical for deployment due to cross-platform incompatibility and high computational cost. Existing quantization-based solutions fail to produce deterministic results across diverse hardware platforms, leading to catastrophic decoding failures. We introduce MLVC, a hardware-robust neural video codec designed for practical cross-platform inference. The key idea is to explicitly transmit scale parameters through the hyperprior, which guarantees entropy coding consistency across devices without requiring bit-exact arithmetic. While this increases bitrate overhead, we recover most of the coding efficiency through architectural improvements (gated memory, ReGLU activation), a long-term reference recovery mechanism, and domain-specific perceptual training. On the VCD video conferencing benchmark, MLVC achieves >70% BD-rate (MOS) improvement over hardware HEVC, the strongest deployable baseline, while reaching subjective quality competitive with DCVC-RT, which cannot operate across diverse platforms. Both the encoder and decoder run at 100 FPS on average on commodity NPUs from Apple, Intel, and Qualcomm. MLVC is the first neural video codec to combine competitive compression performance, real-time speed, and cross-platform robustness across diverse consumer devices, making it suitable for widespread deployment. Code will be released.
Original Article
View Cached Full Text

Cached at: 08/05/26, 01:35 AM

Paper page - MLVC: Multi-platform Learned Video Codec for Real-World Deployment

Source: https://huggingface.co/papers/2606.28027

Abstract

Neuralvideocodecshavesurpassedclassicalcodecsincodingefficiencybutremainimpracticalfordeploymentduetocross-platformincompatibilityandhighcomputationalcost.Existingquantization-basedsolutionsfailtoproducedeterministicresultsacrossdiversehardwareplatforms,leadingtocatastrophicdecodingfailures.WeintroduceMLVC,ahardware-robustneuralvideocodecdesignedforpracticalcross-platforminference.Thekeyideaistoexplicitlytransmitscaleparametersthroughthehyperprior,whichguaranteesentropycodingconsistencyacrossdeviceswithoutrequiringbit-exactarithmetic.Whilethisincreasesbitrateoverhead,werecovermostofthecodingefficiencythrougharchitecturalimprovements(gatedmemory,ReGLUactivation),along-termreferencerecoverymechanism,anddomain-specificperceptualtraining.OntheVCDvideoconferencingbenchmark,MLVCachieves>70%BD-rate(MOS)improvementoverhardwareHEVC,thestrongestdeployablebaseline,whilereachingsubjectivequalitycompetitivewithDCVC-RT,whichcannotoperateacrossdiverseplatforms.Boththeencoderanddecoderrunat100FPSonaverageoncommodityNPUsfromApple,Intel,andQualcomm.MLVCisthefirstneuralvideocodectocombinecompetitivecompressionperformance,real-timespeed,andcross-platformrobustnessacrossdiverseconsumerdevices,makingitsuitableforwidespreaddeployment.Codewillbereleased.

View arXiv pageView PDFGitHub276Add to collection

Get this paper in your agent:

hf papers read 2606\.28027

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.28027 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.28027 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.28027 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

Hugging Face Daily Papers

Mage-VL is an efficient codec-native streaming multimodal foundation model that reduces visual token consumption by over 75% using a custom tokenizer, achieving up to 3.5x inference speedup while matching or outperforming existing models on static and video tasks.

AdaCodec: A Predictive Visual Code for Video MLLMs

Hugging Face Daily Papers

AdaCodec reduces video encoding redundancy in multimodal LLMs by transmitting full visual tokens only when scene prediction fails, otherwise using compact inter-frame change descriptions. It outperforms per-frame RGB baselines at matched token budgets and achieves better or comparable results with significantly fewer tokens, reducing time-to-first-token from 9.26s to 1.62s.

Real-Time Long Video Generation (GitHub Repo)

TLDR AI

NVlabs releases LongLive 2.0, a parallel infrastructure for real-time long video generation using NVFP4 quantization, supporting both training and inference. It achieves 45.7 FPS and is accepted at ICLR 2026.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Papers with Code Trending

VideoChat3 is a fully open, efficient, and generalist video-centric multimodal large language model that introduces Inflated 3D Vision Transformer (I3D-ViT) and Adaptive Frame Resolution for streaming video perception, along with scalable video data synthesis pipelines, achieving superior performance with only 4B parameters.