← Search

Wangguandong Zheng

3 accepted papers

2026

DA$^{2}$: Depth Anything in Any Direction

ICLR 2026poster

Panorama has a full FoV (360$^\circ\times$180$^\circ$), offering a more complete visual description than perspective images. Thanks to this characteristic, panoramic depth estimation is gaining increasing traction in 3D vision. However, due to the scarcity of panoramic data, previous methods are oft…

Cited by 0SourcecodeScholar
2025

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

CVPR 2025poster

Photorealistic 3D human modeling is essential for various applications and has seen tremendous progress. However, existing methods for monocular full-body reconstruction, typically relying on front and/or predicted back view, still struggle with satisfactory performance due to the ill-posed nature o…

2025

SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction

NeurIPS 2025poster

Photorealistic 3D full-body human reconstruction from a single image is a critical yet challenging task for applications in films and video games due to inherent ambiguities and severe self-occlusions. While recent approaches leverage SMPL estimation and SMPL-conditioned image generative models to h…

Cited by 0SourceScholar