Cameras as Rays: Pose Estimation via Ray Diffusion
This work addresses the problem of accurate camera pose estimation for 3D reconstruction in sparse-view scenarios, offering a novel approach with strong performance gains.
The paper tackles the challenge of camera pose estimation from sparsely sampled views by proposing a distributed representation that treats cameras as bundles of rays, coupled with spatial image features. The methods, including regression- and diffusion-based approaches, achieve state-of-the-art performance on CO3D, generalizing to unseen categories and in-the-wild captures.
Estimating camera poses is a fundamental task for 3D reconstruction and remains challenging given sparsely sampled views (<10). In contrast to existing approaches that pursue top-down prediction of global parametrizations of camera extrinsics, we propose a distributed representation of camera pose that treats a camera as a bundle of rays. This representation allows for a tight coupling with spatial image features improving pose precision. We observe that this representation is naturally suited for set-level transformers and develop a regression-based approach that maps image patches to corresponding rays. To capture the inherent uncertainties in sparse-view pose inference, we adapt this approach to learn a denoising diffusion model which allows us to sample plausible modes while improving performance. Our proposed methods, both regression- and diffusion-based, demonstrate state-of-the-art performance on camera pose estimation on CO3D while generalizing to unseen object categories and in-the-wild captures.