CVPR 2025poster1 citations

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}
}
Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild · CVPR 2025