activity
20242026
most citedPSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

2 citations · 2 across the 3 of their papers we have counts for

collaborators

16 papers

cs.CV2026

OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields

Yanqin Jiang, Tengfei Wang, Zhengwei Wang +6

Previous feed-forward 4D reconstruction methods either predict per-frame static point clouds, ignoring foreground motion, or estimate point cloud trajectories while being limited t…

cs.CV2026

LUNA: Learning Universal 3D Human Animation Beyond Skinning

Peng Li, Rawal Khirodkar, Junxuan Li +6

Creating photorealistic, animatable 3D human avatars from monocular images still largely depends on Linear Blend Skinning (LBS) and parametric body models, which constrain expressi…

cs.CV20262 cited

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

Peng Li, Wangguandong Zheng, Yuan Liu +9

Detailed and photorealistic 3D human modeling is essential for various applications and has seen tremendous progress. However, full-body reconstruction from a monocular RGB image r…

cs.CV2026

Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning

Xinyu Liu, Hangjie Yuan, Yujie Wei +9

Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vi…

cs.CV2026

UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass

Mengfei Li, Peng Li, Zheng Zhang +9

We present UniSH, a unified, feed-forward framework for joint metric-scale 3D scene and human reconstruction. A key challenge in this domain is the scarcity of large-scale, annotat…

cs.CV2025

CogniEdit: Dense Gradient Flow Optimization for Fine-Grained Image Editing

Yan Li, Lin Liu, Xiaopeng Zhang +4

Instruction-based image editing with diffusion models has achieved impressive results, yet existing methods struggle with fine-grained instructions specifying precise attributes su…