Eess 3 JAN, 2026

Seamlessly Natural: Image Stitching with Natural Appearance Preservation

Seamlessly Natural: Image Stitching with Natural Appearance Preservation

Results

We compare our approach against several state-of-the-art methods, including LPC , APAP , ELA , SPW , UDIS , EPISNET, UDIS++ and Seamless . We utilized publicly available and widely recognized datasets provided by Nie et al. , and Jia et al. . Please feel free to zoom in on the images to better observe the highlighted elements. Rectangles indicate areas of excessive distortion, while circles mark other types of artifacts or defects that can be localized in the images.

The results obtained with ELA and APAP (In the right-hand column) clearly illustrate the artifacts caused by an inaccurate homography estimation: the resulting image appears severely distorted. In contrast, our method (SENA) demonstrates robustness even in such extreme cases, successfully aligning the images while preserving their natural appearance.

The results obtained with ELA and APAP (In the right-hand column) clearly illustrate the artifacts caused by an inaccurate homography estimation: the resulting image appears severely distorted. In contrast, our method (SENA) demonstrates robustness even in such extreme cases, successfully aligning the images while preserving their natural appearance.

Our method (SENA) preserves geometry and texture consistency across parallax variations.

Our method (SENA) preserves geometry and texture consistency across parallax variations.

Our method (SENA) preserves geometry and texture consistency across parallax variations.

Our method (SENA) preserves geometry and texture consistency across parallax variations.

Our method (SENA) preserves geometry and texture consistency across parallax variations.

Our method (SENA) preserves geometry and texture consistency across parallax variations.

Our method (SENA) preserves geometry and texture consistency across parallax variations.

Our method (SENA) preserves geometry and texture consistency across parallax variations.

Our method (SENA) preserves geometry and texture consistency across parallax variations.

Our method (SENA) preserves geometry and texture consistency across parallax variations.

SEAMLESS and Our Approach.

SEAMLESS and Our Approach.

APAP, ELA, LPC, SPW, UDIS, UDIS++, and OURS.

APAP, ELA, LPC, SPW, UDIS, UDIS++, and OURS.

Results of APAP , LPC , and OURS.

Results of APAP , LPC , and OURS.

APAP, ELA, UDIS and OURS

APAP, ELA, UDIS and OURS