Zobrazeno 1 - 10
of 123
pro vyhledávání: '"Weinmann, Michael"'
We propose a novel cross-spectral rendering framework based on 3D Gaussian Splatting (3DGS) that generates realistic and semantically meaningful splats from registered multi-view spectrum and segmentation maps. This extension enhances the representat
Externí odkaz:
http://arxiv.org/abs/2408.06975
Learning-based scene representations such as neural radiance fields or light field networks, that rely on fitting a scene model to image observations, commonly encounter challenges in the presence of inconsistencies within the images caused by occlus
Externí odkaz:
http://arxiv.org/abs/2312.09780
Autor:
Trunz, Elena, Klein, Jonathan, Müller, Jan, Bode, Lukas, Sarlette, Ralf, Weinmann, Michael, Klein, Reinhard
We investigate the capabilities of neural inverse procedural modeling to infer high-quality procedural yarn models with fiber-level details from single images of depicted yarn samples. While directly inferring all parameters of the underlying yarn mo
Externí odkaz:
http://arxiv.org/abs/2303.00154
Publikováno v:
In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2023, pp. 4258-4272
Despite the impressive progress of telepresence systems for room-scale scenes with static and dynamic scene entities, expanding their capabilities to scenarios with larger dynamic environments beyond a fixed size of a few square-meters remains challe
Externí odkaz:
http://arxiv.org/abs/2211.14310
Extracting high-level structural information from 3D point clouds is challenging but essential for tasks like urban planning or autonomous driving requiring an advanced understanding of the scene at hand. Existing approaches are still not able to pro
Externí odkaz:
http://arxiv.org/abs/2210.13305
We present incomplete gamma kernels, a generalization of Locally Optimal Projection (LOP) operators. In particular, we reveal the relation of the classical localized $ L_1 $ estimator, used in the LOP operator for surface reconstruction from noisy po
Externí odkaz:
http://arxiv.org/abs/2205.01087
Non-line-of-sight reconstruction (NLoS) is a novel indirect imaging modality that aims to recover objects or scene parts outside the field of view from measurements of light that is indirectly scattered off a directly visible, diffuse wall. Despite r
Externí odkaz:
http://arxiv.org/abs/2203.08657
Autor:
Chen, Kaiqiang, Dong, Bo, Wang, Zhirui, Cheng, Peirui, Yan, Menglong, Sun, Xian, Weinmann, Michael, Weinmann, Martin
Publikováno v:
In ISPRS Journal of Photogrammetry and Remote Sensing September 2024 215:383-399
Partial Differential Equations (PDEs) are notoriously difficult to solve. In general, closed-form solutions are not available and numerical approximation schemes are computationally expensive. In this paper, we propose to approach the solution of PDE
Externí odkaz:
http://arxiv.org/abs/2109.07143
Novel view synthesis is required in many robotic applications, such as VR teleoperation and scene reconstruction. Existing methods are often too slow for these contexts, cannot handle dynamic scenes, and are limited by their explicit depth estimation
Externí odkaz:
http://arxiv.org/abs/2106.13139