arXiv:1804.07492
Graph-based Hypothesis Generation for Parallax-tolerant Image Stitching
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
StabStitch++: Unsupervised Online Video Stitching with Spatiotemporal Bidirectional Warps
Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
Modification Takes Courage: Seamless Image Stitching via Reference-Driven Inpainting
Neural Light Spheres for Implicit Image Stitching and View Synthesis
Parallax-tolerant Image Stitching via Segmentation-guided Multi-homography Warping
Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.