# SemanticStitch: Enhancing Image Coherence through Foreground-Aware Seam Carving

arXiv: https://arxiv.org/abs/2511.12084 · HTML: https://mlsanity.com/paper/2511.12084/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 45 references that are in the map.
- First posted on arXiv 15 Nov 2025.

## Builds on (most cited first, 13 of 13)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization](https://mlsanity.com/paper/2303.14189/) (2023)
- [Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priors](https://mlsanity.com/paper/2103.11298/) (2021)
- [Content-Aware Unsupervised Deep Homography Estimation](https://mlsanity.com/paper/1909.05983/) (2019)
- [Adversarial Spatio-Temporal Learning for Video Deblurring](https://mlsanity.com/paper/1804.00533/) (2018)
- [Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images](https://mlsanity.com/paper/2106.12859/) (2021)
- [MB-TaylorFormer V2: Improved Multi-branch Linear Transformer Expanded by Taylor Formula for Image Restoration](https://mlsanity.com/paper/2501.04486/) (2025)
- [Parallax-Tolerant Unsupervised Deep Image Stitching](https://mlsanity.com/paper/2302.08207/) (2023)
- [Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation](https://mlsanity.com/paper/2209.05968/) (2022)
- [GridFormer: Point-Grid Transformer for Surface Reconstruction](https://mlsanity.com/paper/2401.02292/) (2024)
- [Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks](https://mlsanity.com/paper/2402.15959/) (2024)
- [Multi-Spectral Image Stitching via Spatial Graph Reasoning](https://mlsanity.com/paper/2307.16741/) (2023)
- [Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model](https://mlsanity.com/paper/2404.14951/) (2024)

## Abstract (arXiv)

Image stitching often faces challenges due to varying capture angles, positional differences, and object movements, leading to misalignments and visual discrepancies. Traditional seam carving methods neglect semantic information, causing disruptions in foreground continuity. We introduce SemanticStitch, a deep learning-based framework that incorporates semantic priors of foreground objects to preserve their integrity and enhance visual coherence. Our approach includes a novel loss function that emphasizes the semantic integrity of salient objects, significantly improving stitching quality. We also present two specialized real-world datasets to evaluate our method's effectiveness. Experimental results demonstrate substantial improvements over traditional techniques, providing robust support for practical applications.