The More You See in 2D, the More You Perceive in 3D

Xinyang Han*1, Zelin Gao*2, Angjoo Kanazawa1, Shubham Goel†3, Yossi Gandelsman†1,
1 UC Berkeley, 2 Zhejiang University, 3 Avataar
Paper arXiv Code

3D from one or more unposed views. Our system reconstructs the 3D shape and texture of an object with a variable number of real input images. The first, second, and third rows show reconstructions from 1, 3, and 5 input images. The quality of 3D shape and texture improves with more views.

Abstract

Humans can infer 3D structure from 2D images of an object based on past experience and improve their 3D understanding as they see more images. Inspired by this behavior, we introduce SAP3D, a system for 3D reconstruction and novel view synthesis from an arbitrary number of unposed images. Given a few unposed images of an object, we adapt a pre-trained view-conditioned diffusion model together with the camera poses of the images via test-time fine-tuning. The adapted diffusion model and the obtained camera poses are then utilized as instance-specific priors for 3D reconstruction and novel view synthesis. We show that as the number of input images increases, the performance of our approach improves, bridging the gap between optimization-based prior-less 3D reconstruction methods and single-image-to-3D diffusion-based methods. We demonstrate our system on real images as well as standard synthetic benchmarks. Our ablation studies confirm that this adaption behavior is key for more accurate 3D understanding.

Framework

Overview of SAP3D. We first compute coarse relative camera poses using an off-the-shelf model. We fine-tune a view-conditioned 2D diffusion model on the input images and simultaneously refine the camera poses via optimization. The resulting instance-specific diffusion model and camera poses enable 3D reconstruction and novel view synthesis from an arbitrary number of input images.

Results

3D reconstructions with one or more images. Qualitative visualizations with 1, 3, and 5 views for SAP3D on real images (left column) and instances from the synthetic GSO dataset (right column). Observe how the wings of the eagle, the spiky weapon of the green turtle, and the yellow bunny's bouquet of flowers, all become more detailed and accurate with more views.

To view more results and ablations, please visit this page.

BibTeX

@misc{sap3d,
      title={The More You See in 2D, the More You Perceive in 3D}, 
      author={Xinyang Han and Zelin Gao and Angjoo Kanazawa and Shubham Goel and Yossi Gandelsman},
      year={2024},
      eprint={2404.03652},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}