Yuxuan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuxuan Zhang has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Jiaming Liu
Alibaba Group, Hangzhou, China
2 shared publications - Yiren Song
National University of Singapore, Singapore, Singapore
2 shared publications - Binbin Huang
University of Hong Kong, Hong Kong SAR, China
1 shared publication - Hai Ci
National University of Singapore
1 shared publication - Huaxia Li
Xiaohongshu Inc., Shanghai, China
1 shared publication - Jinpeng Yu
ShanghaiTech University & Xiaohongshu Inc., Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-9
StableMakeup: When Real-World Makeup Transfer Meets Diffusion Model
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessStableMakeup: When Real-World Makeup Transfer Meets Diffusion Model
- Open Access
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
ProcessPainter: Learning to draw from sequence data
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessProcessPainter: Learning to draw from sequence data
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8952-8961
GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer
Point cloud completion aims to recover accurate global geometry and preserve fine-grained local details from partial point clouds. Conventional methods typically predict unseen points directly from 3D point cloud coordinates or use self-projected multi-view depth maps to ease this task. However, these gray-scale depth maps cannot reach multi-view consistency, consequently restricting the performance. In this paper, we introduce a GeoFormer that simultaneously enhances the global geometric structure of the points and improves the local details. Specifically, we design a CCM Feature Enhanced Point Generator to integrate image features from multi-view consistent canonical coordinate maps (CCMs) and align them with pure point features, thereby enhancing the global geometry feature. Additionally, we employ the Multi-scale Geometry-aware Upsampler module to progressively enhance local details. This is achieved through cross attention between the multi-scale features extracted from the partial input and the features derived from previously estimated points. Extensive experiments on the PCN, ShapeNet-55/34, and KITTI benchmarks demonstrate that our GeoFormer outperforms recent methods, achieving the state-of-the-art performance. Our code is available at https://github.com/Jinpeng-Yu/GeoFormer.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8952-8961
Open AccessGeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer
Point cloud completion aims to recover accurate global geometry and preserve fine-grained local details from partial point clouds. Conventional methods typically predict unseen points directly from 3D point cloud coordinates or use self-projected multi-view depth maps to ease this task. However, these gray-scale depth maps cannot reach multi-view consistency, consequently restricting the performance. In this paper, we introduce a GeoFormer that simultaneously enhances the global geometric structure of the points and improves the local details. Specifically, we design a CCM Feature Enhanced Point Generator to integrate image features from multi-view consistent canonical coordinate maps (CCMs) and align them with pure point features, thereby enhancing the global geometry feature. Additionally, we employ the Multi-scale Geometry-aware Upsampler module to progressively enhance local details. This is achieved through cross attention between the multi-scale features extracted from the partial input and the features derived from previously estimated points. Extensive experiments on the PCN, ShapeNet-55/34, and KITTI benchmarks demonstrate that our GeoFormer outperforms recent methods, achieving the state-of-the-art performance. Our code is available at https://github.com/Jinpeng-Yu/GeoFormer.