Robust Image Stitching with Optimal Plane
Lang Nie, Yuan Mei, Kang Liao, Yunqiu Xu, Chunyu Lin, Bin Xiao

TL;DR
RopStitch is an unsupervised deep image stitching framework that enhances robustness and naturalness by combining dual-branch feature extraction with optimal plane estimation to handle diverse real-world scenes effectively.
Contribution
The paper introduces a novel dual-branch architecture and a virtual optimal plane concept to improve robustness and content preservation in image stitching.
Findings
Outperforms existing methods in robustness across various datasets
Effectively balances content alignment and structural preservation
Achieves high naturalness in stitched images
Abstract
We present \textit{RopStitch}, an unsupervised deep image stitching framework with both robustness and naturalness. To ensure the robustness of \textit{RopStitch}, we propose to incorporate the universal prior of content perception into the image stitching model by a dual-branch architecture. It separately captures coarse and fine features and integrates them to achieve highly generalizable performance across diverse unseen real-world scenes. Concretely, the dual-branch model consists of a pretrained branch to capture semantically invariant representations and a learnable branch to extract fine-grained discriminative features, which are then merged into a whole by a controllable factor at the correlation level. Besides, considering that content alignment and structural preservation are often contradictory to each other, we propose a concept of virtual optimal planes to relieve this…
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.
