Locally Non-rigid Registration for Mobile HDR Photography
Orazio Gallo (1), Alejandro Troccoli (1), Jun Hu (1, 2), Kari Pulli, (1, 3), Jan Kautz (1) ((1) NVIDIA, (2) Duke University, (3) Light)

TL;DR
This paper introduces a fast, mobile-friendly image registration method for HDR photography that effectively prevents artifacts caused by camera motion and scene changes, enabling high-quality results on portable devices.
Contribution
The paper presents a novel, extremely fast registration technique tailored for mobile HDR imaging that balances accuracy and speed, outperforming existing methods in real-time applications.
Findings
Registration under 700ms on a tablet for 5MP images
Prevents artifacts caused by motion and scene changes
Achieves high-quality HDR composites in real-time
Abstract
Image registration for stack-based HDR photography is challenging. If not properly accounted for, camera motion and scene changes result in artifacts in the composite image. Unfortunately, existing methods to address this problem are either accurate, but too slow for mobile devices, or fast, but prone to failing. We propose a method that fills this void: our approach is extremely fast---under 700ms on a commercial tablet for a pair of 5MP images---and prevents the artifacts that arise from insufficient registration quality.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Image Enhancement Techniques · Robotics and Sensor-Based Localization
