Fine Dense Alignment of Image Bursts through Camera Pose and Depth Estimation
This addresses alignment challenges in burst photography for applications like image restoration and 3D reconstruction, though it appears incremental as it builds on prior dense correspondence methods.
The paper tackles the problem of fine alignment of handheld camera image bursts by optimizing camera motion and dense surface geometry, outperforming existing optical flow methods on synthetic data without training.
This paper introduces a novel approach to the fine alignment of images in a burst captured by a handheld camera. In contrast to traditional techniques that estimate two-dimensional transformations between frame pairs or rely on discrete correspondences, the proposed algorithm establishes dense correspondences by optimizing both the camera motion and surface depth and orientation at every pixel. This approach improves alignment, particularly in scenarios with parallax challenges. Extensive experiments with synthetic bursts featuring small and even tiny baselines demonstrate that it outperforms the best optical flow methods available today in this setting, without requiring any training. Beyond enhanced alignment, our method opens avenues for tasks beyond simple image restoration, such as depth estimation and 3D reconstruction, as supported by promising preliminary results. This positions our approach as a versatile tool for various burst image processing applications.