iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views
This addresses the need for accurate 3D reconstruction in scenarios where camera poses are unavailable, such as in robotics or AR/VR, though it builds incrementally on existing diffusion models.
The paper tackles the problem of 3D object reconstruction from only two views with unknown camera poses, which is challenging due to pose estimation failures in sparse scenarios, and achieves strong performance in both pose estimation and novel view synthesis, enhancing various reconstruction methods.
We present iFusion, a novel 3D object reconstruction framework that requires only two views with unknown camera poses. While single-view reconstruction yields visually appealing results, it can deviate significantly from the actual object, especially on unseen sides. Additional views improve reconstruction fidelity but necessitate known camera poses. However, assuming the availability of pose may be unrealistic, and existing pose estimators fail in sparse view scenarios. To address this, we harness a pre-trained novel view synthesis diffusion model, which embeds implicit knowledge about the geometry and appearance of diverse objects. Our strategy unfolds in three steps: (1) We invert the diffusion model for camera pose estimation instead of synthesizing novel views. (2) The diffusion model is fine-tuned using provided views and estimated poses, turned into a novel view synthesizer tailored for the target object. (3) Leveraging registered views and the fine-tuned diffusion model, we reconstruct the 3D object. Experiments demonstrate strong performance in both pose estimation and novel view synthesis. Moreover, iFusion seamlessly integrates with various reconstruction methods and enhances them.