Fine Dense Alignment of Image Bursts through Camera Pose and Depth Estimation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2023

Fine Dense Alignment of Image Bursts through Camera Pose and Depth Estimation

Abstract

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.
Fichier principal
Vignette du fichier
Fine_Dense_Alignment_of_Image_Bursts_through_Camera_Pose_and_Depth_Estimation (1).pdf (14.72 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04337706 , version 1 (12-12-2023)

Licence

Identifiers

Cite

Bruno Lecouat, Yann Dubois de Mont-Marin, Théo Bodrito, Julien Mairal, Jean Ponce. Fine Dense Alignment of Image Bursts through Camera Pose and Depth Estimation. 2023. ⟨hal-04337706⟩
93 View
18 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More