3 papers
cs.CV2026
Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation
Min-Seop Kwak, Junho Kim, Sangdoo Yun +4
We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology. Unlike prior methods that require…
cs.CV2025
LieHMR: Autoregressive Human Mesh Recovery with Diffusion
Donghwan Kim, Tae-Kyun Kim
We tackle the problem of Human Mesh Recovery (HMR) from a single RGB image, formulating it as an image-conditioned human pose and shape generation. While recovering 3D human pose f…
cs.CV2024
Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images
Donghwan Kim, Tae-Kyun Kim
3D human shape reconstruction under severe occlusion due to human-object or human-human interaction is a challenging problem. Parametric models i.e., SMPL(-X), which are based on t…