logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

A Unified multi-modality conditional latent diffusion model for point cloud generation

delete2025-11-13
delete0
PRE
AI
Y
Yihang Yang
Z
Zibo Zhao
F
Fukun Yin
W
Wen Liu
Y
Yuhan Ding
B
Biao Jiang
G
Gang Yu
陈涛 cover
陈涛 (Tao Chen)
DOI：10.1016/j.patcog.2025.112716delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• A multi-modality conditional point cloud generation method in a unified framework. • Compressing point clouds into a normalized latent space for better data distribution. • Multi-modality conditional generation on latent space for inference speed and quality.

Journal

Pattern Recognition cover
Pattern Recognition
IF:
7.6
Papers:
1.3W
Citations:
4.5W

Organization

F
fudan university
Scholars:
11.6W
Papers: 7.7W
Citations: 121
T
tencent pcg
Scholars:
2
Papers: 1
Citations: 0
S
ShanghaiTech University
Scholars:
9.6K
Papers: 5.9K
Citations: 1.6W
researcher View more organizations