6 papers
HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars
Byungjun Kim, Shunsuke Saito, Giljoo Nam +4
We present a universal prior model for 3D head avatars with explicit hair compositionality. Existing approaches to build generalizable priors for 3D head avatars often adopt a holi…
REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning
Jihyun Lee, Weipeng Xu, Alexander Richard +7
We present REWIND (Real-Time Egocentric Whole-Body Motion Diffusion), a one-step diffusion model for real-time, high-fidelity human motion estimation from egocentric image inputs.…
3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
Zhaoxi Chen, Jiaxiang Tang, Yuhao Dong +10
The increasing demand for high-quality 3D assets across various industries necessitates efficient and automated 3D content creation. Despite recent advancements in 3D generative mo…
Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos
Gengshan Yang, Andrea Bajcsy, Shunsuke Saito +1
We present Agent-to-Sim (ATS), a framework for learning interactive behavior models of 3D agents from casual longitudinal video collections. Different from prior works that rely on…
InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion
Jihyun Lee, Shunsuke Saito, Giljoo Nam +2
We present InterHandGen, a novel framework that learns the generative prior of two-hand interaction. Sampling from our model yields plausible and diverse two-hand shapes in close i…
GALA: Generating Animatable Layered Assets from a Single Scan
Taeksoo Kim, Byungjun Kim, Shunsuke Saito +1
We present GALA, a framework that takes as input a single-layer clothed 3D human mesh and decomposes it into complete multi-layered 3D assets. The outputs can then be combined with…