Creating high-fidelity, animatable 3D avatars from a single image remains a formidable challenge. We identified three desirable attributes of avatar generation: 1) the method should be feed-forward, 2) model a 360° full-head, and 3) should be animati... read more
Digital subtraction angiography (DSA) plays a central role in the diagnosis and treatment of cerebrovascular disease, yet its invasive nature and high acquisition cost severely limit large-scale data collection and public data sharing. Therefore, we ... read more
Ill-posed imaging inverse problems remain challenging due to the ambiguity in mapping degraded observations to clean images. Diffusion-based generative priors have recently shown promise, but typically rely on computationally intensive iterative samp... read more
Procedural generation techniques in 3D rendering engines have revolutionized the creation of complex environments, reducing reliance on manual design. Recent approaches using Large Language Models (LLMs) for 3D scene generation show promise but often... read more
This article addresses the issue of estimating observation parameters (response and error parameters) in inverse problems. The focus is on cases where regularization is introduced in a Bayesian framework and the prior is modeled by a diffusion proces... read more
We propose GSO-SLAM, a real-time monocular dense SLAM system that leverages Gaussian scene representation. Unlike existing methods that couple tracking and mapping with a unified scene, incurring computational costs, or loosely integrate them with we... read more
E-commerce product understanding demands by nature, strong multimodal comprehension from text, images, and structured attributes. General-purpose Vision-Language Models (VLMs) enable generalizable multimodal latent modelling, yet there is no document... read more
Probabilistic forecasting of irregularly sampled time series is crucial in domains such as healthcare and finance, yet it remains a formidable challenge. Existing Neural Controlled Differential Equation (Neural CDE) approaches, while effective at mod... read more
Feature-importance methods show promise in transforming machine learning models from predictive engines into tools for scientific discovery. However, due to data sampling and algorithmic stochasticity, expressive models can be unstable, leading to in... read more
Recent advances in diffusion-based generative models have established a new paradigm for image and video relighting. However, extending these capabilities to 4D relighting remains challenging, due primarily to the scarcity of paired 4D relighting tra... read more
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.