Ziyi Wang

11

Papers

32

Total Citations

Papers (11)

RecDiffusion: Rectangling for Image Stitching with Diffusion Models

SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance

UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting

SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation

PoinTr: Diverse Point Cloud Completion With Geometry-Aware Transformers

Towards Interpretable Deep Metric Learning With Structural Matching

Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models

PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds

UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling

Recognizing Actions from Robotic View for Natural Human-Robot Interaction

P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting