CVApr 20, 2018

Graph-based Hypothesis Generation for Parallax-tolerant Image Stitching

arXiv:1804.07492v1
Originality Incremental advance
AI Analysis

This work addresses image stitching challenges for applications like panoramic photography, but it is incremental as it builds upon existing seam-driven approaches.

The paper tackles the problem of parallax-tolerant image stitching by proposing a graph-based hypothesis generation and seam-guided local alignment, resulting in a significant reduction in the number of hypotheses and improved naturalness of stitching results compared to the state-of-the-art SEAGULL method.

The seam-driven approach has been proven fairly effective for parallax-tolerant image stitching, whose strategy is to search for an invisible seam from finite representative hypotheses of local alignment. In this paper, we propose a graph-based hypothesis generation and a seam-guided local alignment for improving the effectiveness and the efficiency of the seam-driven approach. The experiment demonstrates the significant reduction of number of hypotheses and the improved quality of naturalness of final stitching results, comparing to the state-of-the-art method SEAGULL.

Foundations

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

Your Notes