Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Brachmann, Eric"'
Autor:
Brachmann, Eric, Wynn, Jamie, Chen, Shuai, Cavallari, Tommaso, Monszpart, Áron, Turmukhambetov, Daniyar, Prisacariu, Victor Adrian
We address the task of estimating camera parameters from a set of images depicting a scene. Popular feature-based structure-from-motion (SfM) tools solve this task by incremental reconstruction: they repeat triangulation of sparse 3D points and regis
Externí odkaz:
http://arxiv.org/abs/2404.14351
Pose regression networks predict the camera pose of a query image relative to a known environment. Within this family of methods, absolute pose regression (APR) has recently shown promising accuracy in the range of a few centimeters in position error
Externí odkaz:
http://arxiv.org/abs/2404.09884
Publikováno v:
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Given two images, we can estimate the relative camera pose between them by establishing image-to-image correspondences. Usually, correspondences are 2D-to-2D and the pose we estimate is defined only up to scale. Some applications, aiming at instant a
Externí odkaz:
http://arxiv.org/abs/2404.06337
Humans perceive and construct the world as an arrangement of simple parametric models. In particular, we can often describe man-made environments using volumetric primitives such as cuboids or cylinders. Inferring these primitives is important for at
Externí odkaz:
http://arxiv.org/abs/2403.10452
Autor:
Hodan, Tomas, Sundermeyer, Martin, Labbe, Yann, Nguyen, Van Nguyen, Wang, Gu, Brachmann, Eric, Drost, Bertram, Lepetit, Vincent, Rother, Carsten, Matas, Jiri
We present the evaluation methodology, datasets and results of the BOP Challenge 2023, the fifth in a series of public competitions organized to capture the state of the art in model-based 6D object pose estimation from an RGB/RGB-D image and related
Externí odkaz:
http://arxiv.org/abs/2403.09799
Autor:
Barroso-Laguna, Axel, Brachmann, Eric, Prisacariu, Victor Adrian, Brostow, Gabriel J., Turmukhambetov, Daniyar
Publikováno v:
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Camera pose estimation for two-view geometry traditionally relies on RANSAC. Normally, a multitude of image correspondences leads to a pool of proposed hypotheses, which are then scored to find a winning model. The inlier count is generally regarded
Externí odkaz:
http://arxiv.org/abs/2306.01596
Learning-based visual relocalizers exhibit leading pose accuracy, but require hours or days of training. Since training needs to happen on each new scene again, long training times make learning-based relocalization impractical for most applications,
Externí odkaz:
http://arxiv.org/abs/2305.14059
Autor:
Sundermeyer, Martin, Hodan, Tomas, Labbe, Yann, Wang, Gu, Brachmann, Eric, Drost, Bertram, Rother, Carsten, Matas, Jiri
We present the evaluation methodology, datasets and results of the BOP Challenge 2022, the fourth in a series of public competitions organized with the goal to capture the status quo in the field of 6D object pose estimation from an RGB/RGB-D image.
Externí odkaz:
http://arxiv.org/abs/2302.13075
Autor:
Arnold, Eduardo, Wynn, Jamie, Vicente, Sara, Garcia-Hernando, Guillermo, Monszpart, Áron, Prisacariu, Victor Adrian, Turmukhambetov, Daniyar, Brachmann, Eric
Can we relocalize in a scene represented by a single reference image? Standard visual relocalization requires hundreds of images and scale calibration to build a scene-specific 3D map. In contrast, we propose Map-free Relocalization, i.e., using only
Externí odkaz:
http://arxiv.org/abs/2210.05494
Benchmark datasets that measure camera pose accuracy have driven progress in visual re-localisation research. To obtain poses for thousands of images, it is common to use a reference algorithm to generate pseudo ground truth. Popular choices include
Externí odkaz:
http://arxiv.org/abs/2109.00524