Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild
Junhyeong Cho, Kim Youwang, Hunmin Yang, Tae-Hyun Oh
Abstract
Recent monocular 3D shape reconstruction methods have shown promising zero-shot results on object-segmented images without any occlusions. However, their effectiveness is significantly compromised in real-world conditions, due to imperfect object segmentation by off-the-shelf models and the prevalence of occlusions. To effectively address these issues, we propose a unified regression model that integrates segmentation and reconstruction, specifically designed for occlusion-aware 3D shape reconstruction. To facilitate its reconstruction in the wild, we also introduce a scalable data synthesis pipeline that simulates a wide range of variations in objects, occluders, and backgrounds. Training on our synthetic data enables the proposed model to achieve state-of-the-art zero-shot results on real-world images, using significantly fewer parameters than competing approaches.
BibTeX
@InProceedings{Cho_2025_CVPR,
author = {Cho, Junhyeong and Youwang, Kim and Yang, Hunmin and Oh, Tae-Hyun},
title = {Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild},
booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)},
month = {June},
year = {2025},
pages = {22786-22798}
}