1 citations · 1 across the 11 of their papers we have counts for
12 papers
Q-MAGIC: Quad-only Mesh Autoregressive Generation via Singularity-Aware Circular Relative Offset Tokenization
Yuming Zhao, Zezeng Li, Weimin Wang +2
Autoregressive models have proven effective for triangular mesh generation by transforming it into predicting the next face, converting the non-differentiable connectivity predicti…
PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation
Zezeng Li, Enda Xiang, Thuy Tran +3
Imitation learning has enabled remarkable progress in robotic manipulation, especially with diffusion and flow-based policies that generate complex visuomotor behaviors directly fr…
ADPro: a Test-time Adaptive Diffusion Policy via Manifold-constrained Denoising and Task-aware Initialization for Robotic Manipulation
Zezeng Li, Rui Yang, Ruochen Chen +2
Diffusion policies have recently emerged as a powerful class of visuomotor controllers for robot manipulation, offering stable training and expressive multi-modal action modeling.…
Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challenges
Zezeng Li, Alexandre Chapin, Enda Xiang +6
Robotic Manipulation (RM) is central to the advancement of autonomous robots, enabling them to interact with and manipulate objects in real-world environments. This survey focuses…
NoPain: No-box Point Cloud Attack via Optimal Transport Singular Boundary
Zezeng Li, Xiaoyu Du, Na Lei +2
Adversarial attacks exploit the vulnerability of deep models against adversarial samples. Existing point cloud attackers are tailored to specific models, iteratively optimizing per…
Point2Quad: Generating Quad Meshes from Point Clouds via Face Prediction
Zezeng Li, Zhihui Qi, Weimin Wang +3
Quad meshes are essential in geometric modeling and computational mechanics. Although learning-based methods for triangle mesh demonstrate considerable advancements, quad mesh gene…
MergeNet: Explicit Mesh Reconstruction from Sparse Point Clouds via Edge Prediction
Weimin Wang, Yingxu Deng, Zezeng Li +2
This paper introduces a novel method for reconstructing meshes from sparse point clouds by predicting edge connection. Existing implicit methods usually produce superior smooth and…
HOTS3D: Hyper-Spherical Optimal Transport for Semantic Alignment of Text-to-3D Generation
Zezeng Li, Weimin Wang, Yuming Zhao +3
Recent CLIP-guided 3D generation methods have achieved promising results but struggle with generating faithful 3D shapes that conform with input text due to the gap between text an…
Point Cloud Compression via Constrained Optimal Transport
Zezeng Li, Weimin Wang, Ziliang Wang +1
This paper presents a novel point cloud compression method COT-PCC by formulating the task as a constrained optimal transport (COT) problem. COT-PCC takes the bitrate of compressed…
DPM-OT: A New Diffusion Probabilistic Model Based on Optimal Transport
Zezeng Li, ShengHao Li, Zhanpeng Wang +3
Sampling from diffusion probabilistic models (DPMs) can be viewed as a piecewise distribution transformation, which generally requires hundreds or thousands of steps of the inverse…
OT-Net: A Reusable Neural Optimal Transport Solver
Zezeng Li, Shenghao Li, Lianbao Jin +2
With the widespread application of optimal transport (OT), its calculation becomes essential, and various algorithms have emerged. However, the existing methods either have low eff…
What's the Situation with Intelligent Mesh Generation: A Survey and Perspectives
Na Lei, Zezeng Li, Zebin Xu +2
Intelligent Mesh Generation (IMG) represents a novel and promising field of research, utilizing machine learning techniques to generate meshes. Despite its relative infancy, IMG ha…