Daeyun Shin

PhD, until 2026, now at Google

Advised by Charless Fowlkes

Personal homepage

Publications

Everybody Tracking Every Body

Daeyun Shin, Yunhan Zhao, Shu Kong, Alexander C. Berg, Charless Fowlkes

arXiv:2608.29927, 2026. preprint

Abstract PDF arXiv
Objects, Scenes, and People: from Observation to Reconstruction

Daeyun Shin

PhD Thesis, University of California, Irvine, 2026.

Abstract PDF
Geometric Pose Affordance: Monocular 3D Human Pose Estimation with Scene Constraints

Zhe Wang, Liyan Chen, Shaurya Rathore, Daeyun Shin, Charless C. Fowlkes

ECCV Workshops (6), 3-18, 2022.

Abstract PDF arXiv DOI
Modular Framework for Visuomotor Language Grounding

Kolby Nottingham, Litian Liang, Daeyun Shin, Charless C. Fowlkes, Roy Fox, Sameer Singh

CVPR Workshops, 2021.

Abstract PDF arXiv
Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation

Yunhan Zhao, Shu Kong, Daeyun Shin, Charless C. Fowlkes

CVPR, 3327-3337, 2020.

Abstract PDF CVPR arXiv DOI
Predicting Camera Viewpoint Improves Cross-Dataset Generalization for 3D Human Pose Estimation

Zhe Wang, Daeyun Shin, Charless C. Fowlkes

ECCV Workshops (2), 523-540, 2020.

Abstract PDF arXiv DOI
3D Scene Reconstruction With Multi-Layer Depth and Epipolar Transformers

Daeyun Shin, Zhile Ren, Erik B. Sudderth, Charless C. Fowlkes

ICCV, 2172-2182, 2019.

Abstract PDF ICCV DOI
Multi-layer Depth and Epipolar Feature Transformers for 3D Scene Reconstruction

Daeyun Shin, Zhile Ren, Erik B. Sudderth, Charless C. Fowlkes

CVPR Workshops, 39-43, 2019.

Abstract PDF arXiv
Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction

Daeyun Shin, Charless Fowlkes, Derek Hoiem

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3061-3069, 2018.

Abstract PDF arXiv DOI