CTRL-C: Camera calibration TRansformer with Line-Classification

• URL: http://arxiv.org/abs/2109.02259v1
• Date: Mon, 6 Sep 2021 06:30:38 GMT
• Title: CTRL-C: Camera calibration TRansformer with Line-Classification
• Authors: Jinwoo Lee and Hyunsung Go and Hyunjoon Lee and Sunghyun Cho and Minhyuk Sung and Junho Kim
• Abstract summary: We propose Camera calibration TRansformer with Line-Classification (CTRL-C), an end-to-end neural network-based approach to single image camera calibration. Our experiments demonstrate that benchmark-C outperforms the previous state-of-the-art methods on the Google Street View and SUN360 datasets.
• Score: 22.092637979495358
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Single image camera calibration is the task of estimating the camera parameters from a single input image, such as the vanishing points, focal length, and horizon line. In this work, we propose Camera calibration TRansformer with Line-Classification (CTRL-C), an end-to-end neural network-based approach to single image camera calibration, which directly estimates the camera parameters from an image and a set of line segments. Our network adopts the transformer architecture to capture the global structure of an image with multi-modal inputs in an end-to-end manner. We also propose an auxiliary task of line classification to train the network to extract the global geometric information from lines effectively. Our experiments demonstrate that CTRL-C outperforms the previous state-of-the-art methods on the Google Street View and SUN360 benchmark datasets.

Related papers

• SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries [0.0]
  We introduce textitmulti-Scale defOrmable transFormer for camera calibratIon for enhanced line queries, SOFI. SOFI improves the line queries used in MSC-C and MSCC by using both line content and line geometric features. It outperforms existing methods on the textit Google Street View, textit Horizon Line in the Wild, and textit Holicity datasets while keeping a competitive inference speed.
  arXiv  Detail & Related papers  (2024-09-23T21:17:38Z)
• LiFCal: Online Light Field Camera Calibration via Bundle Adjustment [38.2887165481751]
  LiFCal is an online calibration pipeline for MLA-based light field cameras. It accurately determines model parameters from a moving camera sequence without precise calibration targets. It can be applied in a target-free scene, and it is implemented online in a complete and continuous pipeline.
  arXiv  Detail & Related papers  (2024-08-21T15:04:49Z)
• Anyview: Generalizable Indoor 3D Object Detection with Variable Frames [63.51422844333147]
  We present a novel 3D detection framework named AnyView for our practical applications. Our method achieves both great generalizability and high detection accuracy with a simple and clean architecture.
  arXiv  Detail & Related papers  (2023-10-09T02:15:45Z)
• Deep Learning for Camera Calibration and Beyond: A Survey [100.75060862015945]
  Camera calibration involves estimating camera parameters to infer geometric features from captured sequences. Recent efforts show that learning-based solutions have the potential to be used in place of the repeatability works of manual calibrations.
  arXiv  Detail & Related papers  (2023-03-19T04:00:05Z)
• CVLNet: Cross-View Semantic Correspondence Learning for Video-based Camera Localization [89.69214577915959]
  This paper tackles the problem of Cross-view Video-based camera localization. We propose estimating the query camera's relative displacement to a satellite image before similarity matching. Experiments have demonstrated the effectiveness of video-based localization over single image-based localization.
  arXiv  Detail & Related papers  (2022-08-07T07:35:17Z)
• Self-Supervised Camera Self-Calibration from Video [34.35533943247917]
  We propose a learning algorithm to regress per-sequence calibration parameters using an efficient family of general camera models. Our procedure achieves self-calibration results with sub-pixel reprojection error, outperforming other learning-based methods.
  arXiv  Detail & Related papers  (2021-12-06T19:42:05Z)
• Unsupervised Depth Completion with Calibrated Backprojection Layers [79.35651668390496]
  We propose a deep neural network architecture to infer dense depth from an image and a sparse point cloud. It is trained using a video stream and corresponding synchronized sparse point cloud, as obtained from a LIDAR or other range sensor, along with the intrinsic calibration parameters of the camera. At inference time, the calibration of the camera, which can be different from the one used for training, is fed as an input to the network along with the sparse point cloud and a single image.
  arXiv  Detail & Related papers  (2021-08-24T05:41:59Z)
• TransCamP: Graph Transformer for 6-DoF Camera Pose Estimation [77.09542018140823]
  We propose a neural network approach with a graph transformer backbone, namely TransCamP, to address the camera relocalization problem. TransCamP effectively fuses the image features, camera pose information and inter-frame relative camera motions into encoded graph attributes.
  arXiv  Detail & Related papers  (2021-05-28T19:08:43Z)
• How to Calibrate Your Event Camera [58.80418612800161]
  We propose a generic event camera calibration framework using image reconstruction. We show that neural-network-based image reconstruction is well suited for the task of intrinsic and extrinsic calibration of event cameras.
  arXiv  Detail & Related papers  (2021-05-26T07:06:58Z)
• Neural Geometric Parser for Single Image Camera Calibration [17.393543270903653]
  We propose a neural geometric learning single image camera calibration for man-made scenes. Our approach considers both semantic and geometric cues, resulting in significant accuracy improvement. The experimental results reveal that the performance of our neural approach is significantly higher than that of existing state-of-the-art camera calibration techniques.
  arXiv  Detail & Related papers  (2020-07-23T08:29:00Z)
• On-line non-overlapping camera calibration net [2.4569090161971743]
  We propose an on-line method of the inter-camera pose estimation. Experiments with simulations and the KITTI dataset show the proposed method to be effective in simulation.
  arXiv  Detail & Related papers  (2020-02-19T04:59:11Z)

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.