analiza aiqbench
AnyView addresses a critical gap in generative video models by achieving spatiotemporal consistency across arbitrary viewpoints in highly dynamic scenes, overcoming the limitations of current baselines that rely on significant viewpoint overlap. By training on diverse data sources ranging from monocular to multi-view dynamic datasets, this diffusion-based framework enables zero-shot novel view synthesis without heavy geometric assumptions. The introduction of AnyViewBench provides a necessary evaluation standard for testing extreme dynamic scenarios where existing methods typically fail.
AnyView: Synthesizing Any Novel View in Dynamic Scenes
arXiv:2601.16982v2 Announce Type: replace-cross Abstract: Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consistency in highly dynamic real-world environments. In this work, we introduce $\textbf{AnyView}$, a diffusion-based video generation framework for $\textit{dynamic view synthesis}$ with minimal inductive biases or geometric assumptions. We leverage multiple data sources with various levels of supervision, including monocular (2D), multi-view static (3D) and multi-view dynamic (4D) datasets, to train a generalist spatiotemporal implicit representation capable of producing zero-shot novel videos from arbitrary camera locations and trajectories. We evaluate AnyView on standard benchmarks, showing competitive results with the current state of the art, and propose $\textbf{AnyViewBench}$, a challenging new benchmark tailored towards $\textit{extreme}$ dynamic view synthesis in diverse real-world scenarios. In this more dramatic setting, we find that most baselines drastically degrade in performance, as they require significant overlap between viewpoints, while AnyView maintains the ability to produce realistic, plausible, and spatiotemporally consistent videos when prompted from $\textit{any}$ viewpoint. Results, data, code, and models can be viewed at: https://tri-ml.github.io/AnyView/
Abstract:Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consistency in highly dynamic real-world environments. In this work, we introduce $\textbf{AnyView}$, a diffusion-based video generation framework for $\textit{dynamic view synthesis}$ with minimal inductive biases or geometric assumptions. We leverage multiple data sources with various levels of supervision, including monocular (2D), multi-view static (3D) and multi-view dynamic (4D) datasets, to train a generalist spatiotemporal implicit representation capable of producing zero-shot novel videos from arbitrary camera locations and trajectories. We evaluate AnyView on standard benchmarks, showing competitive results with the current state of the art, and propose $\textbf{AnyViewBench}$, a challenging new benchmark tailored towards $\textit{extreme}$ dynamic view synthesis in diverse real-world scenarios. In this more dramatic setting, we find that most baselines drastically degrade in performance, as they require significant overlap between viewpoints, while AnyView maintains the ability to produce realistic, plausible, and spatiotemporally consistent videos when prompted from $\textit{any}$ viewpoint. Results, data, code, and models can be viewed at: this https URL
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Robotics (cs.RO)
arXiv:2601.16982 [cs.CV]
(or arXiv:2601.16982v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2601.16982 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.
Text integral sub licența deschisă a publicației · 269 cuvinte
Subiecte conexe
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
arXiv · 28 iul. 2026
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
arXiv · 3 iun. 2026
Tariffs didn’t bring manufacturing jobs back to the US
The Verge · 27 iul. 2026
[AINews] not much happened today
Latent Space · 3 oct. 2026