CVApr 7, 2015

Locally Non-rigid Registration for Mobile HDR Photography

arXiv:1504.01441v351 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of efficient and accurate HDR photography for mobile users, representing an incremental improvement over prior methods.

The paper tackled the problem of image registration for stack-based HDR photography on mobile devices, where existing methods are either too slow or prone to artifacts, and achieved a fast registration time of under 700ms on a commercial tablet for a pair of 5MP images while preventing artifacts.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes