collaborators

7 papers

cs.CV2026

Efficient RWKV-based Representation Learning for 3D Point Clouds

Yun Liu, Xuefeng Yan, Liangliang Nan +5

The recent receptance weighted key value (RWKV) model combines RNN-style recurrence, offering a linear-complexity alternative to Transformers' quadratic self-attention for modeling…

cs.CV2026

BridgeShape: Latent Diffusion Schrödinger Bridge for 3D Shape Completion

Dequan Kong, Honghua Chen, Zhe Zhu +1

Existing diffusion-based 3D shape completion methods typically use a conditional paradigm, injecting incomplete shape information into the denoising network via deep feature intera…

cs.CV2026

CoreEditor: Correspondence-constrained Diffusion for Consistent 3D Editing

Zhe Zhu, Honghua Chen, Peng Li +1

Text-driven 3D editing seeks to modify 3D scenes according to textual descriptions, and most existing approaches tackle this by adapting pre-trained 2D image editors to multi-view…

cs.CV2025

BSGS: Bi-stage 3D Gaussian Splatting for Camera Motion Deblurring

An Zhao, Piaopiao Yu, Zhe Zhu +1

3D Gaussian Splatting has exhibited remarkable capabilities in 3D scene reconstruction. However, reconstructing high-quality 3D scenes from motion-blurred images caused by camera m…

cs.CV2025

PointSFDA: Source-free Domain Adaptation for Point Cloud Completion

Xing He, Zhe Zhu, Liangliang Nan +3

Conventional methods for point cloud completion, typically trained on synthetic datasets, face significant challenges when applied to out-of-distribution real-world scans. In this…

cs.CV2025

GenPC: Zero-shot Point Cloud Completion via 3D Generative Priors

An Li, Zhe Zhu, Mingqiang Wei

Existing point cloud completion methods, which typically depend on predefined synthetic training datasets, encounter significant challenges when applied to out-of-distribution, rea…