Fangzhou Cheng | Searcharxiv

arXiv2026

AnyView: Synthesizing Any Novel View in Dynamic Scenes

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 \emph{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 \emph{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 \emph{any} viewpoint. Results, data, code, and models can be viewed at: https://tri-ml.github.io/AnyView/

cs.CV↗

arXiv2017

Layer dependent role of collagen recruitment during loading of the rat bladder wall

In this work, we reevaluated long standing conjectures as to the source of the exceptionally large compliance of the bladder wall. Whereas, these conjectures were based on indirect measures of loading mechanisms, in this work we take advantage of advances in bioimaging to directly assess collagen fibers and wall architecture during loading. A custom biaxial mechanical testing system compatible with multiphoton microscopy (MPM) was used to directly measure the layer dependent collagen fiber recruitment in bladder tissue from 9 male Fischer rats (4 adult and 5 aged). As for other soft tissues, the bladder loading curve was exponential in shape and could be divided into toe, transition and high stress regimes. The relationship between collagen recruitment and loading curves were evaluated in the context of the inner bladder wall (lamina propria) and outer detrusor smooth muscle layer. The large extensibility of the bladder was found to be possible due to folds in the wall (rugae) that provide a mechanism for low resistance flattening without any discernible recruitment of collagen fibers throughout the toe regime. For elastic bladders, as the loading extended into the transition regime, a gradual coordinated recruitment of collagen fibers between the lamina propria and detrusor smooth muscle layers was found. A second important finding is that wall extensibility could be lost by premature recruitment of collagen in the outer wall that cut short the toe region. This work provides, for the first time, a mechanistic understanding of the role of collagen recruitment in determining bladder capacitance.

q-bio.TO↗