https://github.com/genji970/3d-vision-paper-

paper explanation and use records.(3d vision 논문들 해석, 활용 기록용)
https://github.com/genji970/3d-vision-paper-

Last synced: about 1 month ago
JSON representation

paper explanation and use records.(3d vision 논문들 해석, 활용 기록용)

• Host: GitHub
• URL: https://github.com/genji970/3d-vision-paper-
• Owner: genji970
• License: mit
• Created: 2025-04-01T02:09:15.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2025-04-11T13:02:18.000Z (about 2 months ago)
• Last Synced: 2025-04-27T07:46:46.410Z (about 1 month ago)
• Size: 31.3 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# 3d-vision-paper-

paper explanation and use records.(3d vision 논문들 해석, 활용 기록용)

1. Advancing 3D Medical Image Analysis with  Variable Dimension Transform based Supervised 3D Pre-training

   Shu Zhang, Zihao Li, Hong-Yu Zhou, Jiechao Ma and Yizhou Yu, Fellow, IEEE

2. MVSFORMER++: REVEALING THE DEVIL IN TRANSFORMER’S DETAILS FOR MULTI-VIEW STEREO

   Chenjie Cao1,2,3∗†, Xinlin Ren3∗, Yanwei Fu1‡ 1 School of Data Science, Fudan University, 2 Alibaba Group

 3 School of Computer Science, Fudan University {cjcao20,xlren20,yanweifu}@fudan.edu.cn

3. Human Pose as Compositional Tokens

   Zigang Geng1,3 , Chunyu Wang3*, Yixuan Wei2,3, Ze Liu1,3, Houqiang Li1, Han Hu3*

 1University of Science and Technology of China 2Tsinghua University 3Microsoft Research Asia

(아직 일부)