Object-IR: Leveraging Object Consistency and Mesh Deformation for Self-Supervised Image Retargeting

Eliminating geometric distortion in semantically important regions remains an intractable challenge in image retargeting. This paper presents Object-IR, a self-supervised architecture that reformulates image retargeting as a learning-based mesh warping optimization problem, where the mesh deformation is guided by object appearance consistency and geometric-preserving constraints. Given an input image and a target aspect ratio, we initialize a uniform rigid mesh at the output resolution and use a convolutional neural network to predict the motion of each mesh grid and obtain the deformed mesh. The retargeted result is generated by warping the input image according to the rigid mesh in the input image and the deformed mesh in the output resolution. To mitigate geometric distortion, we design a comprehensive objective function incorporating a) object-consistent loss to ensure that the important semantic objects retain their appearance, b) geometric-preserving loss to constrain simple scale transform of the important meshes, and c) boundary loss to enforce a clean rectangular output. Notably, our self-supervised paradigm eliminates the need for manually annotated retargeting datasets by deriving supervision directly from the input's geometric and semantic properties. Extensive evaluations on the RetargetMe benchmark demonstrate that our Object-IR achieves state-of-the-art performance, outperforming existing methods in quantitative metrics and subjective visual quality assessments. The framework efficiently processes arbitrary input resolutions (average inference time: 0.009s for 1024x683 resolution) while maintaining real-time performance on consumer-grade GPUs. The source code will soon be available at https://github.com/tlliao/Object-IR.

DyGLNet: Hybrid Global-Local Feature Fusion with Dynamic Upsampling for Medical Image Segmentation

Medical image segmentation grapples with challenges including multi-scale lesion variability, ill-defined tissue boundaries, and computationally intensive processing demands. This paper proposes the DyGLNet, which achieves efficient and accurate segmentation by fusing global and local features with a dynamic upsampling mechanism. The model innovatively designs a hybrid feature extraction module (SHDCBlock), combining single-head self-attention and multi-scale dilated convolutions to model local details and global context collaboratively. We further introduce a dynamic adaptive upsampling module (DyFusionUp) to realize high-fidelity reconstruction of feature maps based on learnable offsets. Then, a lightweight design is adopted to reduce computational overhead. Experiments on seven public datasets demonstrate that DyGLNet outperforms existing methods, particularly excelling in boundary accuracy and small-object segmentation. Meanwhile, it exhibits lower computation complexity, enabling an efficient and reliable solution for clinical medical image analysis. The code will be made available soon.

Parallax-tolerant Image Stitching via Segmentation-guided Multi-homography Warping

Large parallax between images is an intractable issue in image stitching. Various warping-based methods are proposed to address it, yet the results are unsatisfactory. In this paper, we propose a novel image stitching method using multi-homography warping guided by image segmentation. Specifically, we leverage the Segment Anything Model to segment the target image into numerous contents and partition the feature points into multiple subsets via the energy-based multi-homography fitting algorithm. The multiple subsets of feature points are used to calculate the corresponding multiple homographies. For each segmented content in the overlapping region, we select its best-fitting homography with the lowest photometric error. For each segmented content in the non-overlapping region, we calculate a weighted combination of the linearized homographies. Finally, the target image is warped via the best-fitting homographies to align with the reference image, and the final panorama is generated via linear blending. Comprehensive experimental results on the public datasets demonstrate that our method provides the best alignment accuracy by a large margin, compared with the state-of-the-art methods. The source code is available at https://github.com/tlliao/multi-homo-warp.

Seam-guided local alignment and stitching for large parallax images

Seam-cutting methods have been proven effective in the composition step of image stitching, especially for images with parallax. However, the effectiveness of seam-cutting usually depends on that images can be roughly aligned such that there exists a local region where a plausible seam can be found. For images with large parallax, current alignment methods often fall short of expectations. In this paper, we propose a local alignment and stitching method guided by seam quality evaluation. First, we use existing image alignment and seam-cutting methods to calculate an initial seam and evaluate the quality of pixels along the seam. Then, for pixels with low qualities, we separate their enclosing patches in the aligned images and locally align them by extracting modified dense correspondences via SIFT flow. Finally, we composite the aligned patches via seam-cutting and merge them into the original aligned result to generate the final mosaic. Experiments show that compared with the state-of-the-art seam-cutting methods, our result is more plausible and with fewer artifacts. The code will be available at https://github.com/tlliao/Seam-guided-local-alignment.

Natural Image Stitching Using Depth Maps

Natural image stitching (NIS) aims to create one natural-looking mosaic from two overlapping images that capture a same 3D scene from different viewing positions. Challenges inevitably arise when the scene is non-planar and the camera baseline is wide, since parallax becomes not negligible in such cases. In this paper, we propose a novel NIS method using depth maps, which generates natural-looking mosaics against parallax in both overlapping and non-overlapping regions. Firstly, we estimate a pixel-to-pixel transformation based on feature matches and their depth values. Then, we draw a triangulation of the target image and estimate multiple local homographies, one per triangle, based on the locations of their vertices and the rectified depth values. Finally, the warping image is composited by the backward mapping of piece-wise homographies. Experimental results demonstrate that the proposed method not only provides accurate alignment in the overlapping regions, but also virtual naturalness in the non-overlapping region.

Learning-based Natural Geometric Matching with Homography Prior

Geometric matching is a key step in computer vision tasks. Previous learning-based methods for geometric matching concentrate more on improving alignment quality, while we argue the importance of naturalness issue simultaneously. To deal with this, firstly, Pearson correlation is applied to handle large intra-class variations of features in feature matching stage. Then, we parametrize homography transformation with 9 parameters in full connected layer of our network, to better characterize large viewpoint variations compared with affine transformation. Furthermore, a novel loss function with Gaussian weights guarantees the model accuracy and efficiency in training procedure. Finally, we provide two choices for different purposes in geometric matching. When compositing homography with affine transformation, the alignment accuracy improves and all lines are preserved, which results in a more natural transformed image. When compositing homography with non-rigid thin-plate-spline transformation, the alignment accuracy further improves. Experimental results on Proposal Flow dataset show that our method outperforms state-of-the-art methods, both in terms of alignment accuracy and naturalness.

Coarse-to-fine Seam Estimation for Image Stitching

Seam-cutting and seam-driven techniques have been proven effective for handling imperfect image series in image stitching. Generally, seam-driven is to utilize seam-cutting to find a best seam from one or finite alignment hypotheses based on a predefined seam quality metric. However, the quality metrics in most methods are defined to measure the average performance of the pixels on the seam without considering the relevance and variance among them. This may cause that the seam with the minimal measure is not optimal (perception-inconsistent) in human perception. In this paper, we propose a novel coarse-to-fine seam estimation method which applies the evaluation in a different way. For pixels on the seam, we develop a patch-point evaluation algorithm concentrating more on the correlation and variation of them. The evaluations are then used to recalculate the difference map of the overlapping region and reestimate a stitching seam. This evaluation-reestimation procedure iterates until the current seam changes negligibly comparing with the previous seams. Experiments show that our proposed method can finally find a nearly perception-consistent seam after several iterations, which outperforms the conventional seam-cutting and other seam-driven methods.

Graph-based Hypothesis Generation for Parallax-tolerant Image Stitching

The seam-driven approach has been proven fairly effective for parallax-tolerant image stitching, whose strategy is to search for an invisible seam from finite representative hypotheses of local alignment. In this paper, we propose a graph-based hypothesis generation and a seam-guided local alignment for improving the effectiveness and the efficiency of the seam-driven approach. The experiment demonstrates the significant reduction of number of hypotheses and the improved quality of naturalness of final stitching results, comparing to the state-of-the-art method SEAGULL.

Ratio-Preserving Half-Cylindrical Warps for Natural Image Stitching

A novel warp for natural image stitching is proposed that utilizes the property of cylindrical warp and a horizontal pixel selection strategy. The proposed ratio-preserving half-cylindrical warp is a combination of homography and cylindrical warps which guarantees alignment by homography and possesses less projective distortion by cylindrical warp. Unlike previous approaches applying cylindrical warp before homography, we use partition lines to divide the image into different parts and apply homography in the overlapping region while a composition of homography and cylindrical warps in the non-overlapping region. The pixel selection strategy then samples the points in horizontal and reconstructs the image via interpolation to further reduce horizontal distortion by maintaining the ratio as similarity. With applying half-cylindrical warp and horizontal pixel selection, the projective distortion in vertical and horizontal is mitigated simultaneously. Experiments show that our warp is efficient and produces a more natural-looking stitched result than previous methods.

Single-Perspective Warps in Natural Image Stitching

Results of image stitching can be perceptually divided into single-perspective and multiple-perspective. Compared to the multiple-perspective result, the single-perspective result excels in perspective consistency but suffers from projective distortion. In this paper, we propose two single-perspective warps for natural image stitching. The first one is a parametric warp, which is a combination of the as-projective-as-possible warp and the quasi-homography warp via dual-feature. The second one is a mesh-based warp, which is determined by optimizing a total energy function that simultaneously emphasizes different characteristics of the single-perspective warp, including alignment, naturalness, distortion and saliency. A comprehensive evaluation demonstrates that the proposed warp outperforms some state-of-the-art warps, including homography, APAP, AutoStitch, SPHP and GSP.