3 papers
cs.CV2026
DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction
Yufu Wang, Evonne Ng, Soyong Shin +8
We present DuoMo, a generative method that recovers human motion in world-space coordinates from unconstrained videos with noisy or incomplete observations. Reconstructing such mot…
cs.CV2025
3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt
Lukas Höllein, Aljaž BožiÄ, Michael Zollhöfer +1
We present 3DGS-LM, a new method that accelerates the reconstruction of 3D Gaussian Splatting (3DGS) by replacing its ADAM optimizer with a tailored Levenberg-Marquardt (LM). Exist…
cs.CV2025
Drivable 3D Gaussian Avatars
Wojciech Zielonka, Timur Bagautdinov, Shunsuke Saito +3
We present Drivable 3D Gaussian Avatars (D3GA), a multi-layered 3D controllable model for human bodies that utilizes 3D Gaussian primitives embedded into tetrahedral cages. The adv…