activity
20232025
most citedCoSeR: Bridging Image and Language for Cognitive Super-Resolution

3 citations · 7 across the 10 of their papers we have counts for

collaborators

11 papers

cs.CV2025

Zero-P-to-3: Zero-Shot Partial-View Images to 3D Object

Yuxuan Lin, Ruihang Chu, Zhenyu Chen +9

Generative 3D reconstruction shows strong potential in incomplete observations. While sparse-view and single-image reconstruction are well-researched, partial observation remains u…

cs.CV2025

Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation

Shiyong Liu, Zhihao Li, Xiao Tang +1

Most model-based 3D hand pose and shape estimation methods directly regress the parametric model parameters from an image to obtain 3D joints under weak supervision. However, these…

cs.GR2025

OccluGaussian: Occlusion-Aware Gaussian Splatting for Large Scene Reconstruction and Rendering

Shiyong Liu, Xiao Tang, Zhihao Li +6

In large-scale scene reconstruction using 3D Gaussian splatting, it is common to partition the scene into multiple smaller regions and reconstruct them individually. However, exist…

cs.CV2025

Decoupling Appearance Variations with 3D Consistent Features in Gaussian Splatting

Jiaqi Lin, Zhihao Li, Binxiao Huang +6

Gaussian Splatting has emerged as a prominent 3D representation in novel view synthesis, but it still suffers from appearance variations, which are caused by various factors, such…

cs.CV2024

MagicEraser: Erasing Any Objects via Semantics-Aware Control

Fan Li, Zixiao Zhang, Yi Huang +4

The traditional image inpainting task aims to restore corrupted regions by referencing surrounding background and foreground. However, the object erasure task, which is in increasi…

cs.CV2024

TraDiffusion: Trajectory-Based Training-Free Image Generation

Mingrui Wu, Oucheng Huang, Jiayi Ji +6

In this work, we propose a training-free, trajectory-based controllable T2I approach, termed TraDiffusion. This novel method allows users to effortlessly guide image generation via…