Cvpr Websites
Tae-Hyun Oh @ KAIST
Tae-Hyun Oh, Dept. of EE., KAIST, South Korea.
Mid-Level Visual Features Improve Generalization and Sample Efficienct
Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Active Tasks. UC Berkeley, FAIR, Stanford. A large-scale study of how to use pretrained perception networks for performing active tasks..
Denoising Diffusion-based Generative Modeling: Foundations and Applica
Tutorial in Conjunction with CVPR 2022 ---
Denoising Diffusion Models: A Generative Learning Big Bang
Tutorial in Conjunction with CVPR 2023 ---
3D Scene Generation
Website for the Workshop on 3D Scene Generation at CVPR 2019 ---
Prompting in Vision
CVPR 2023 Tutorial on Prompting in Vision
Taskonomy
Taskonomy: Disentangling Task Transfer Learning, CVPR 2018 (Best Paper). Stanford, UC Berkeley. We propose a fully computational approach for modeling the structure in the space of visual tasks.
L3DS @CVPR21
Language for 3D Scenes, CVPR 2021 Workshop
Learning Generative Models of 3D Structures
Website for the tutorial on learning generative models of 3D structures at Eurographics 2019 ---
Learning 3D Generative Models
Website for the Workshop on Learning 3D Generative Models at CVPR 2020 ---
Fourth Workshop on Image Matching: Local Features & Beyond
Image Matching: Local Features & Beyond - CVPR 2024 Workshop
Rolling Shutter Camera: Modeling, Optimization, Learning, and Hardware
Tutorial in Conjunction with CVPR 2023 ---
Synchroinzation and Cycle Consistency in Computer Vision
CVPR 2020 Tutorial on Synchronization and Cycle Consistency in Computer Vision.