Zixuan Huang

12

Papers

117

Total Citations

Papers (12)

SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement

ZeroShape: Regression-based Zero-shot Shape Reconstruction

PointInfinity: Resolution-Invariant Point Diffusion Models

Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation

ShapeClipper: Scalable 3D Shape Learning From Single-View Images via Geometric and CLIP-Based Consistency

Planes vs. Chairs: Category-Guided 3D Shape Learning without Any 3D Cues

Adversarial Robustness via Deformable Convolution with Stochasticity

SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images

ReGCL: Rethinking Message Passing in Graph Contrastive Learning

Interpretable and Accurate Fine-grained Recognition via Region Grouping

Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization

Low-shot Object Learning with Mutual Exclusivity Bias