Image and Video Processing

Seamlessly Natural Image Stitching with Natural Appearance Preservation

Reading time: 4 minute
...
#paper #research

📝 Original Paper Info

- Title: Seamlessly Natural Image Stitching with Natural Appearance Preservation
- ArXiv ID: 2601.01257
- Date: 2026-01-03
- Authors: Gaetane Lorna N. Tchana, Damaris Belle M. Fotso, Antonio Hendricks, Christophe Bobda

📝 Abstract

This paper introduces SENA (SEamlessly NAtural), a geometry-driven image stitching approach that prioritizes structural fidelity in challenging real-world scenes characterized by parallax and depth variation. Conventional image stitching relies on homographic alignment, but this rigid planar assumption often fails in dual-camera setups with significant scene depth, leading to distortions such as visible warps and spherical bulging. SENA addresses these fundamental limitations through three key contributions. First, we propose a hierarchical affine-based warping strategy, combining global affine initialization with local affine refinement and smooth free-form deformation. This design preserves local shape, parallelism, and aspect ratios, thereby avoiding the hallucinated structural distortions commonly introduced by homography-based models. Second, we introduce a geometry-driven adequate zone detection mechanism that identifies parallax-minimized regions directly from the disparity consistency of RANSAC-filtered feature correspondences, without relying on semantic segmentation. Third, building upon this adequate zone, we perform anchor-based seamline cutting and segmentation, enforcing a one-to-one geometric correspondence across image pairs by construction, which effectively eliminates ghosting, duplication, and smearing artifacts in the final panorama. Extensive experiments conducted on challenging datasets demonstrate that SENA achieves alignment accuracy comparable to leading homography-based methods, while significantly outperforming them in critical visual metrics such as shape preservation, texture integrity, and overall visual realism.

💡 Summary & Analysis

1. **Introduction to the New Methodology**: - Our approach (SENA) focuses on maintaining geometric and texture consistency across parallax variations, ensuring that images align naturally without distortion.

  1. Accurate Homography Estimation:

    • SENA minimizes distortions and artifacts caused by inaccurate homography estimation compared to existing methods like APAP or ELA. This is akin to making sure every part of a puzzle fits perfectly in its place.

  2. Robust Performance:

    • SENA showcases superior performance across various image processing tasks, outperforming several state-of-the-art methods.

📄 Full Paper Content (ArXiv Source)

# 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.


Input images

image
APAP

image
ELA

image
OURS


input images

image
APAP

image
ELA

image
EPISNET

image
OURS

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.

2

image image
Input images
image
LPC
image
Seamless
image
image image
Input images
image
LPC
image
Seamless
image
Ours (SENA)

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

2

image image
Input images
image
APAP
image
ELA
image
EPISNET
image
Seamless
image
Ours(SENA)
image image
Input images
image
SEAMLESS
image
Ours (SENA)

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

2

image image
Input images
image
APAP
image
ELA
image
UDIS
image
OURS
image image
Input images
image
APAP
image
ELA
image
UDIS
image
Ours (SENA)

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

2

image image
Input images
image
APAP
image
ELA
image
UDIS
image
OURS
image image
Input images
image
APAP
image
ELA
image
UDIS
image
Ours (SENA)

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

2

image image
Input images
image
APAP
image
ELA
image
UDIS
image
OURS
image image
Input images
image
APAP
image
ELA
image
UDIS
image
Ours (SENA)

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


Input images

image
APAP

image
ELA

image
OURS


input images

image
APAP

image
ELA

image
EPISNET

image
OURS

image
source

image
target

image
SEAMLESS

image
OURS

SEAMLESS and Our Approach.

2

image image
Input images
image
APAP
image
ELA
image
LPC

image
SPW
image
UDIS
image
UDIS2
image
OURS

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

image
source

image
target

image
APAP

image
LPC

image
OURS

Results of APAP , LPC , and OURS.


Input images

image
APAP

image
ELA

image
UDIS

image
OURS


Input images

image
APAP

image
ELA

image
UDIS

image
OURS

APAP, ELA, UDIS and OURS

📊 논문 시각자료 (Figures)

Figure 1



Figure 2



Figure 3



Figure 4



Figure 5



Figure 6



Figure 7



Figure 8



Figure 9



Figure 10



Figure 11



Figure 12



Figure 13



Figure 14



Figure 15



Figure 16



Figure 17



Figure 18



Figure 19



Figure 20



Figure 21



Figure 22



Figure 23



Figure 24



Figure 25



Figure 26



Figure 27



Figure 28



Figure 29



Figure 30



Figure 31



Figure 32



Figure 33



Figure 34



Figure 35



Figure 36



Figure 37



Figure 38



Figure 39



Figure 40



Figure 41



Figure 42



Figure 43



Figure 44



Figure 45



Figure 46



Figure 47



Figure 48



Figure 49



Figure 50



Figure 51



Figure 52



Figure 53



Figure 54



Figure 55



Figure 56



Figure 57



Figure 58



Figure 59



Figure 60



Figure 61



Figure 62



Figure 63



Figure 64



Figure 65



Figure 66



Figure 67



Figure 68



Figure 69



Figure 70



Figure 71



Figure 72



Figure 73



Figure 74



Figure 75



Figure 76



Figure 77



Figure 78



Figure 79



Figure 80



Figure 81



Figure 82



Figure 83



Figure 84



Figure 85



Figure 86



Figure 87



Figure 88



Figure 89



Figure 90



Figure 91



Figure 92



Figure 93



Figure 94



Figure 95



Figure 96



Figure 97



Figure 98



Figure 99



Figure 100



Figure 101



Figure 102



Figure 103



Figure 104



Figure 105



Figure 106



Figure 107



Figure 108



Figure 109



Figure 110



Figure 111



Figure 112



Figure 113



Figure 114



Figure 115



Figure 116



Figure 117



Figure 118



Figure 119



Figure 120



Figure 121



Figure 122



Figure 123



Figure 124



Figure 125



Figure 126



Figure 127



Figure 128



Figure 129



Figure 130



Figure 131



Figure 132



Figure 133



Figure 134



Figure 135



Figure 136



Figure 137



Figure 138



Figure 139



Figure 140



Figure 141



Figure 142



Figure 143



Figure 144



Figure 145



Figure 146



Figure 147



Figure 148



Figure 149



Figure 150



Figure 151



Figure 152



Figure 153



Figure 154



Figure 155



Figure 156



Figure 157



Figure 158



Figure 159



Figure 160



Figure 161



Figure 162



Figure 163



Figure 164



Figure 165



Figure 166



Figure 167



Figure 168



Figure 169



Figure 170



Figure 171



Figure 172



Figure 173



Figure 174



Figure 175



Figure 176



Figure 177



Figure 178



Figure 179



Figure 180



Figure 181



Figure 182



Figure 183



Figure 184



Figure 185



Figure 186



Figure 187



Figure 188



Figure 189



Figure 190



Figure 191



Figure 192



Figure 193



Figure 194



Figure 195



Figure 196



Figure 197



Figure 198



Figure 199



Figure 200



Figure 201



Figure 202



Figure 203



Figure 204



Figure 205



Figure 206



Figure 207



Figure 208



Figure 209



Figure 210



Figure 211



Figure 212



Figure 213



Figure 214



Figure 215



Figure 216



Figure 217



Figure 218



Figure 219



Figure 220



Figure 221



Figure 222



Figure 223



Figure 224



Figure 225



Figure 226



Figure 227



Figure 228



Figure 229



Figure 230



Figure 231



Figure 232



Figure 233



Figure 234



Figure 235



Figure 236



Figure 237



Figure 238



Figure 239



Figure 240



Figure 241



Figure 242



Figure 243



Figure 244



Figure 245



Figure 246



Figure 247



Figure 248



Figure 249



Figure 250



Figure 251



Figure 252



Figure 253



Figure 254



Figure 255



Figure 256



Figure 257



Figure 258



Figure 259



Figure 260



Figure 261



Figure 262



Figure 263



Figure 264



Figure 265



Figure 266



Figure 267



Figure 268



Figure 269



Figure 270



Figure 271



Figure 272



Figure 273



Figure 274



Figure 275



Figure 276



A Note of Gratitude

The copyright of this content belongs to the respective researchers. We deeply appreciate their hard work and contribution to the advancement of human civilization.

Related Posts

Start searching

Enter keywords to search articles

↑↓
↵
ESC
⌘K Shortcut