aiqbench analysis
This research addresses critical latency and throughput bottlenecks in video inverse problems by integrating autoregressive diffusion models into a streaming architecture. The proposed AVIS framework significantly reduces initial processing time from 114 seconds to just 4 seconds while improving frame rates, with the accelerated "AVIS Flash" variant reaching nearly 6 FPS on consumer hardware. These advancements move zero-shot video restoration closer to real-time deployment without sacrificing restoration quality.
Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
arXiv:2605.20624v2 Announce Type: replace-cross Abstract: Diffusion models provide powerful priors for zero-shot video inverse problems, but their real-time deployment is hindered by two inefficiencies: high initial latency caused by holistic video restoration, and low throughput resulting from multiple VAE passes to enforce measurement consistency in pixel space. To overcome these limitations, we propose Autoregressive Video Inverse problem Solver (AVIS). The AVIS framework leverages autoregressive video diffusion models to restore videos in a streaming manner, naturally eliminating latency bottlenecks. Specifically, AVIS initializes reverse diffusion with a measurement-consistent estimate, reducing the required sampling steps. Compared to leading non-autoregressive solvers, AVIS drastically reduces initial latency from 114s to 4s and increases throughput from 0.71 to 1.18 FPS while achieving superior restoration quality. We further introduce a highly accelerated variant, dubbed AVIS Flash, that enforces measurement consistency solely on the first chunk. AVIS Flash substantially boosts throughput to 5.91 FPS on a single RTX 4090 GPU while maintaining competitive performance and achieving a favorable efficiency-performance trade-off, paving the way toward real-time deployment.
Abstract:Diffusion models provide powerful priors for zero-shot video inverse problems, but their real-time deployment is hindered by two inefficiencies: high initial latency caused by holistic video restoration, and low throughput resulting from multiple VAE passes to enforce measurement consistency in pixel space. To overcome these limitations, we propose Autoregressive Video Inverse problem Solver (AVIS). The AVIS framework leverages autoregressive video diffusion models to restore videos in a streaming manner, naturally eliminating latency bottlenecks. Specifically, AVIS initializes reverse diffusion with a measurement-consistent estimate, reducing the required sampling steps. Compared to leading non-autoregressive solvers, AVIS drastically reduces initial latency from 114s to 4s and increases throughput from 0.71 to 1.18 FPS while achieving superior restoration quality. We further introduce a highly accelerated variant, dubbed AVIS Flash, that enforces measurement consistency solely on the first chunk. AVIS Flash substantially boosts throughput to 5.91 FPS on a single RTX 4090 GPU while maintaining competitive performance and achieving a favorable efficiency-performance trade-off, paving the way toward real-time deployment.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2605.20624 [cs.CV]
(or arXiv:2605.20624v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2605.20624 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 264 words
Related coverage
Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction
arXiv · Jun 5, 2026
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod
AWS · Sep 4, 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · Sep 25, 2026
Developing Healthcare Robotics with GPU-Native Medical Physics Simulation
NVIDIA · Jul 28, 2026