Implicit Neural Image Stitching

• Main Authors: Kim, Minsu, Lee, Jaewon, Lee, Byeonghun, Im, Sunghoon, Jin, Kyong Hwan
• Format: Journal Article
• Language: English
• Published: 04-09-2023
• Subjects: Computer Science - Computer Vision and Pattern Recognition
• DOI: 10.48550/arxiv.2309.01409

Existing frameworks for image stitching often provide visually reasonable
stitchings. However, they suffer from blurry artifacts and disparities in
illumination, depth level, etc. Although the recent learning-based stitchings
relax such disparities, the required methods impose sacrifice of image
qualities failing to capture high-frequency details for stitched images. To
address the problem, we propose a novel approach, implicit Neural Image
Stitching (NIS) that extends arbitrary-scale super-resolution. Our method
estimates Fourier coefficients of images for quality-enhancing warps. Then, the
suggested model blends color mismatches and misalignment in the latent space
and decodes the features into RGB values of stitched images. Our experiments
show that our approach achieves improvement in resolving the low-definition
imaging of the previous deep image stitching with favorable accelerated
image-enhancing methods. Our source code is available at
https://github.com/minshu-kim/NIS.