INSID3 is a training-free in-context segmentation method that segments objects, parts, and personalized instances from a single annotated reference image using only frozen DINOv...
·
Researchers have introduced ClothTransformer, a framework that reframes cloth simulation as autoregressive sequence modeling inside a learned latent space. A single Transformer ...
·
Researchers have introduced MilliVid, a video generation approach that tackles long-range consistency by structuring the latent space hierarchically across multiple resolutions....
·
Researchers from Insta360 Research, Wuhan University, and collaborating institutions have introduced UniSHARP, a monocular novel view synthesis method capable of handling divers...
StreamForce is a new causal video generation framework that allows users to steer video dynamics in real time through continuous force inputs — both global (scene-wide) and loca...
Researchers from ShanghaiTech University and Deemos Technology have introduced PARSE (Part-Aware Relational Spatial Modeling), a framework that addresses a longstanding limitati...
Researchers at Tsinghua University and Z.ai have released SCAIL-2, a diffusion-based framework for controlled character animation that eliminates reliance on skeleton maps, char...
Researchers from multiple institutions have proposed a splatting-free inverse rendering framework for 3D Gaussian fields that grounds both forward rendering and backward optimiz...
·
Researchers at Abu Dhabi's Mohamed bin Zayed University of Artificial Intelligence have found that Western genres account for 94% of the training data behind leading generative ...
·
Hugging Face engineer Mishig Davaadorj tasked a coding agent with building an interactive website showcasing Paris monuments as 3D Gaussian splats — without touching an image ge...
·
