Zobrazeno 1 - 10
of 159
pro vyhledávání: '"Sattler, Torsten"'
Estimating the relative pose between two cameras is a fundamental step in many applications such as Structure-from-Motion. The common approach to relative pose estimation is to apply a minimal solver inside a RANSAC loop. Highly efficient solvers exi
Externí odkaz:
http://arxiv.org/abs/2410.05984
Visual localization is the problem of estimating the camera pose of a given query image within a known scene. Most state-of-the-art localization approaches follow the structure-based paradigm and use 2D-3D matches between pixels in a query image and
Externí odkaz:
http://arxiv.org/abs/2409.14269
With their meaningful geometry and their omnipresence in the 3D world, edges are extremely useful primitives in computer vision. 3D edges comprise of lines and curves, and methods to reconstruct them use either multi-view images or point clouds as in
Externí odkaz:
http://arxiv.org/abs/2409.12886
Rapid growth in the popularity of AR/VR/MR applications and cloud-based visual localization systems has given rise to an increased focus on the privacy of user content in the localization process. This privacy concern has been further escalated by th
Externí odkaz:
http://arxiv.org/abs/2409.11536
Object pose estimation is essential to many industrial applications involving robotic manipulation, navigation, and augmented reality. Current generalizable object pose estimators, i.e., approaches that do not need to be trained per object, rely on a
Externí odkaz:
http://arxiv.org/abs/2408.08234
While the field of 3D scene reconstruction is dominated by NeRFs due to their photorealistic quality, 3D Gaussian Splatting (3DGS) has recently emerged, offering similar quality with real-time rendering speeds. However, both methods primarily excel w
Externí odkaz:
http://arxiv.org/abs/2407.08447
Autor:
Kulhanek, Jonas, Sattler, Torsten
Novel view synthesis is an important problem with many applications, including AR/VR, gaming, and simulations for robotics. With the recent rapid development of Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) methods, it is becoming d
Externí odkaz:
http://arxiv.org/abs/2406.17345
Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former requires spa
Externí odkaz:
http://arxiv.org/abs/2406.08463
Recently, 3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis results, while allowing the rendering of high-resolution images in real-time. However, leveraging 3D Gaussians for surface reconstruction poses significant challe
Externí odkaz:
http://arxiv.org/abs/2404.10772
Pose refinement is an interesting and practically relevant research direction. Pose refinement can be used to (1) obtain a more accurate pose estimate from an initial prior (e.g., from retrieval), (2) as pre-processing, i.e., to provide a better star
Externí odkaz:
http://arxiv.org/abs/2404.10438