Self-supervised pre-training has revolutionized foundation models for languages, individual 2D images and videos, but remains largely unexplored for learning 3D...
Reinforcement learning (RL), earlier proven to be effective in large language and multi-modal models, has been successfully extended to enhance 2D image generat...
All-in-One Image Restoration (AiOIR) aims to recover high-quality images from diverse degradations within a unified framework. However, existing methods often f...
Recent advances in subject-driven video generation with large diffusion models have enabled personalized content synthesis conditioned on user-provided subjects...
Reasoning goes beyond language; the real world requires reasoning about space, time, affordances, and much more that words alone cannot convey. Existing multimo...
Prior approaches injecting camera control into diffusion models have focused on specific subsets of 4D consistency tasks: novel view synthesis, text-to-video wi...
Although normalization layers have long been viewed as indispensable components of deep learning architectures, the recent introduction of Dynamic Tanh (DyT) ha...
We present Any4D, a scalable multi-view transformer for metric-scale, dense feed-forward 4D reconstruction. Any4D directly generates per-pixel motion and geomet...
Spoor's computer vision software can help wind farms, and other industries, track bird populations and migration patterns....
Recent advances in Gaussian Splatting-based inverse rendering extend Gaussian primitives with shading parameters and physically grounded light transport, enabli...
Video unified models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with ...
Radiance field representations have recently been explored in the latent space of VAEs that are commonly used by diffusion models. This direction offers efficie...
