Object-centered image stitching

• URL: http://arxiv.org/abs/2011.11789v1
• Date: Mon, 23 Nov 2020 23:20:09 GMT
• Title: Object-centered image stitching
• Authors: Charles Herrmann and Chen Wang and Richard Strong Bowen and Emil Keyder and Ramin Zabih
• Abstract summary: Image stitching is typically decomposed into three phases: registration, seam finding, and blending. Here, we observe that the most problematic failures of this approach occur when objects are cropped, omitted, or duplicated. We take an object-centered approach to the problem, leveraging recent advances in object detection.
• Score: 15.850092529468004
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image stitching is typically decomposed into three phases: registration, which aligns the source images with a common target image; seam finding, which determines for each target pixel the source image it should come from; and blending, which smooths transitions over the seams. As described in [1], the seam finding phase attempts to place seams between pixels where the transition between source images is not noticeable. Here, we observe that the most problematic failures of this approach occur when objects are cropped, omitted, or duplicated. We therefore take an object-centered approach to the problem, leveraging recent advances in object detection [2,3,4]. We penalize candidate solutions with this class of error by modifying the energy function used in the seam finding stage. This produces substantially more realistic stitching results on challenging imagery. In addition, these methods can be used to determine when there is non-recoverable occlusion in the input data, and also suggest a simple evaluation metric that can be used to evaluate the output of stitching algorithms.

Related papers

• DeepClean: Integrated Distortion Identification and Algorithm Selection for Rectifying Image Corruptions [1.8024397171920883]
  We propose a two-level sequential planning approach for automated image distortion classification and rectification. The advantage of our approach is its dynamic reconfiguration, conditioned on the input image and generalisability to unseen candidate algorithms at inference time.
  arXiv  Detail & Related papers  (2024-07-23T08:57:11Z)
• Depth-aware Panoptic Segmentation [1.4170154234094008]
  We present a novel CNN-based method for panoptic segmentation. We propose a new depth-aware dice loss term which penalises the assignment of pixels to the same thing instance. Experiments carried out on the Cityscapes dataset show that the proposed method reduces the number of objects that are erroneously merged into one thing instance.
  arXiv  Detail & Related papers  (2024-03-21T08:06:49Z)
• DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses [59.51874686414509]
  Current approaches approximate the continuous pose representation with a large number of discrete pose hypotheses. We present a Deep Voxel Matching Network (DVMNet) that eliminates the need for pose hypotheses and computes the relative object pose in a single pass. Our method delivers more accurate relative pose estimates for novel objects at a lower computational cost compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-03-20T15:41:32Z)
• A 2D Sinogram-Based Approach to Defect Localization in Computed Tomography [3.4916237834391874]
  We present a comprehensive three-step deep learning algorithm to identify and analyze defects within objects without resorting to image reconstruction. Our method achieves the Intersection over Union of 92.02% on our simulated data, with an average position error of 1.3 pixels for defect detection on a 512-pixel-wide detector.
  arXiv  Detail & Related papers  (2024-01-29T12:20:26Z)
• Generalizable Person Re-Identification via Viewpoint Alignment and Fusion [74.30861504619851]
  This work proposes to use a 3D dense pose estimation model and a texture mapping module to map pedestrian images to canonical view images. Due to the imperfection of the texture mapping module, the canonical view images may lose the discriminative detail clues from the original images. We show that our method can lead to superior performance over the existing approaches in various evaluation settings.
  arXiv  Detail & Related papers  (2022-12-05T16:24:09Z)
• Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment [53.401889855278704]
  Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples. We propose a two-stage background suppression and foreground alignment framework, which is composed of a background activation suppression (BAS) module, a foreground object alignment (FOA) module, and a local to local (L2L) similarity metric. Experiments conducted on multiple popular fine-grained benchmarks demonstrate that our method outperforms the existing state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2022-10-04T07:54:40Z)
• An End-to-End Approach for Seam Carving Detection using Deep Neural Networks [0.0]
  Seam carving is a computational method capable of resizing images for both reduction and expansion based on its content, instead of the image geometry. We propose an end-to-end approach to cope with the problem of automatic seam carving detection.
  arXiv  Detail & Related papers  (2022-03-05T12:53:55Z)
• Region-level Active Learning for Cluttered Scenes [60.93811392293329]
  We introduce a new strategy that subsumes previous Image-level and Object-level approaches into a generalized, Region-level approach. We show that this approach significantly decreases labeling effort and improves rare object search on realistic data with inherent class-imbalance and cluttered scenes.
  arXiv  Detail & Related papers  (2021-08-20T14:02:38Z)
• DeepI2P: Image-to-Point Cloud Registration via Deep Classification [71.3121124994105]
  DeepI2P is a novel approach for cross-modality registration between an image and a point cloud. Our method estimates the relative rigid transformation between the coordinate frames of the camera and Lidar. We circumvent the difficulty by converting the registration problem into a classification and inverse camera projection optimization problem.
  arXiv  Detail & Related papers  (2021-04-08T04:27:32Z)
• Learning to Estimate Hidden Motions with Global Motion Aggregation [71.12650817490318]
  Occlusions pose a significant challenge to optical flow algorithms that rely on local evidences. We introduce a global motion aggregation module to find long-range dependencies between pixels in the first image. We demonstrate that the optical flow estimates in the occluded regions can be significantly improved without damaging the performance in non-occluded regions.
  arXiv  Detail & Related papers  (2021-04-06T10:32:03Z)
• Pixel-wise Anomaly Detection in Complex Driving Scenes [30.884375526254836]
  We present a pixel-wise anomaly detection framework that uses uncertainty maps to improve anomaly detection. Our approach works as a general framework around already trained segmentation networks. Top-2 performance across a range of different anomaly datasets shows the robustness of our approach to handling different anomaly instances.
  arXiv  Detail & Related papers  (2021-03-09T14:26:20Z)

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.