UniStitch: Unifying Semantic and Geometric Features for Image Stitching

• URL: http://arxiv.org/abs/2603.10568v1
• Date: Wed, 11 Mar 2026 09:19:34 GMT
• Title: UniStitch: Unifying Semantic and Geometric Features for Image Stitching
• Abstract summary: We present UniStitch, a unified image stitching framework from multimodal features.<n>To align discrete geometric features with continuous semantic feature maps, we present a Neural Point Transformer (NPT) module.<n>An Adaptive Mixture of Experts (AMoE) module is designed to fuse geometric and semantic representations.<n>Experiments show that UniStitch outperforms existing state-of-the-art methods with a large margin.
• Score: 47.900985740008174
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditional image stitching methods estimate warps from hand-crafted geometric features, whereas recent learning-based solutions leverage semantic features from neural networks instead. These two lines of research have largely diverged along separate evolution, with virtually no meaningful convergence to date. In this paper, we take a pioneering step to bridge this gap by unifying semantic and geometric features with UniStitch, a unified image stitching framework from multimodal features. To align discrete geometric features (i.e., keypoint) with continuous semantic feature maps, we present a Neural Point Transformer (NPT) module, which transforms unordered, sparse 1D geometric keypoints into ordered, dense 2D semantic maps. Then, to integrate the advantages of both representations, an Adaptive Mixture of Experts (AMoE) module is designed to fuse geometric and semantic representations. It dynamically shifts focus toward more reliable features during the fusion process, allowing the model to handle complex scenes, especially when either modality might be compromised. The fused representation can be adopted into common deep stitching pipelines, delivering significant performance gains over any single feature. Experiments show that UniStitch outperforms existing state-of-the-art methods with a large margin, paving the way for a unified paradigm between traditional and learning-based image stitching.

Related papers

• Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images [81.94999489820974]
  UniSplat is a feed-forward framework for learning 3D representations from unposed multi-view images.<n>We introduce a dual-masking strategy that strengthens geometry induction in the encoder.<n>Second, we develop a coarse-to-fine Gaussian splatting strategy that reduces appearance-semantics inconsistencies.<n>Third, we introduce a pose-conditioned recalibration mechanism that interrelates predicted 3D point and semantic maps into the image plane.
  arXiv  Detail & Related papers  (2026-04-12T10:36:18Z)
• Geodesic Prototype Matching via Diffusion Maps for Interpretable Fine-Grained Recognition [8.300049635963141]
  We propose a novel paradigm for prototype-based recognition that anchors similarity within the intrinsic geometry of deep features.<n>Specifically, we distill the latent manifold structure of each class into a diffusion space and introduce a differentiable Nystr"om distances.<n>To ensure efficiency, we employ compact per-class landmark sets with periodic updates.
  arXiv  Detail & Related papers  (2025-09-21T12:15:04Z)
• Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation [62.87088388345378]
  We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology.<n>Method leverages off-the-shelf geometry predictors to predict partial geometries viewed from reference images.<n>Cross-modal attention distillation is proposed to ensure accurate alignment between generated images and geometry.
  arXiv  Detail & Related papers  (2025-06-13T16:19:00Z)
• SMLNet: A SPD Manifold Learning Network for Infrared and Visible Image Fusion [60.18614468818683]
  We propose a novel SPD (symmetric positive definite) manifold learning for multi-modal image fusion.<n>Our framework exhibits superior performance compared to the current state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-16T03:09:49Z)
• Self-Supervised Learning from Non-Object Centric Images with a Geometric Transformation Sensitive Architecture [7.825153552141346]
  We propose a Geometric Transformation Sensitive Architecture to be sensitive to geometric transformations. Our method encourages the student to be sensitive by predicting rotation and using targets that vary with those transformations. Our approach demonstrates improved performance when using non-object-centric images as pretraining data.
  arXiv  Detail & Related papers  (2023-04-17T06:32:37Z)
• Parallax-Tolerant Unsupervised Deep Image Stitching [57.76737888499145]
  We propose UDIS++, a parallax-tolerant unsupervised deep image stitching technique. First, we propose a robust and flexible warp to model the image registration from global homography to local thin-plate spline motion. To further eliminate the parallax artifacts, we propose to composite the stitched image seamlessly by unsupervised learning for seam-driven composition masks.
  arXiv  Detail & Related papers  (2023-02-16T10:40:55Z)
• Geo-SIC: Learning Deformable Geometric Shapes in Deep Image Classifiers [8.781861951759948]
  This paper presents Geo-SIC, the first deep learning model to learn deformable shapes in a deformation space for an improved performance of image classification. We introduce a newly designed framework that (i) simultaneously derives features from both image and latent shape spaces with large intra-class variations. We develop a boosted classification network, equipped with an unsupervised learning of geometric shape representations.
  arXiv  Detail & Related papers  (2022-10-25T01:55:17Z)
• NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go [109.88509362837475]
  We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes. NeuroMorph produces smooth and point-to-point correspondences between them. It works well for a large variety of input shapes, including non-isometric pairs from different object categories.
  arXiv  Detail & Related papers  (2021-06-17T12:25:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.