Zobrazeno 1 - 10
of 4 072
pro vyhledávání: '"Cremers P"'
Recent advances in 3D Gaussian Splatting have shown promising results. Existing methods typically assume static scenes and/or multiple images with prior poses. Dynamics, sparse views, and unknown poses significantly increase the problem complexity du
Externí odkaz:
http://arxiv.org/abs/2412.00851
Understanding dynamic 3D scenes is fundamental for various applications, including extended reality (XR) and autonomous driving. Effectively integrating semantic information into 3D reconstruction enables holistic representation that opens opportunit
Externí odkaz:
http://arxiv.org/abs/2411.19290
We present HI-SLAM2, a geometry-aware Gaussian SLAM system that achieves fast and accurate monocular scene reconstruction using only RGB input. Existing Neural SLAM or 3DGS-based SLAM methods often trade off between rendering quality and geometry acc
Externí odkaz:
http://arxiv.org/abs/2411.17982
Simultaneous localization and mapping (SLAM) has achieved impressive performance in static environments. However, SLAM in dynamic environments remains an open question. Many methods directly filter out dynamic objects, resulting in incomplete scene r
Externí odkaz:
http://arxiv.org/abs/2411.15800
In this paper we propose MA-DV2F: Multi-Agent Dynamic Velocity Vector Field. It is a framework for simultaneously controlling a group of vehicles in challenging environments. DV2F is generated for each vehicle independently and provides a map of refe
Externí odkaz:
http://arxiv.org/abs/2411.06404
Autor:
Wysocki, Olaf, Tan, Yue, Froech, Thomas, Xia, Yan, Wysocki, Magdalena, Hoegner, Ludwig, Cremers, Daniel, Holst, Christoph
Facade semantic segmentation is a long-standing challenge in photogrammetry and computer vision. Although the last decades have witnessed the influx of facade segmentation methods, there is a lack of comprehensive facade classes and data covering the
Externí odkaz:
http://arxiv.org/abs/2411.04865
Autor:
Cong, Bai, Daheim, Nico, Shen, Yuesong, Cremers, Daniel, Yokota, Rio, Khan, Mohammad Emtiyaz, Möllenhoff, Thomas
We show that variational learning can significantly improve the accuracy and calibration of Low-Rank Adaptation (LoRA) without a substantial increase in the cost. We replace AdamW by the Improved Variational Online Newton (IVON) algorithm to finetune
Externí odkaz:
http://arxiv.org/abs/2411.04421
Post-training quantization is widely employed to reduce the computational demands of neural networks. Typically, individual substructures, such as layers or blocks of layers, are quantized with the objective of minimizing quantization errors in their
Externí odkaz:
http://arxiv.org/abs/2411.03934
Autor:
Ehm, Viktoria, Amrani, Nafie El, Xie, Yizheng, Bastian, Lennart, Gao, Maolin, Wang, Weikang, Sang, Lu, Cao, Dongliang, Lähner, Zorah, Cremers, Daniel, Bernard, Florian
Finding correspondences between 3D shapes is an important and long-standing problem in computer vision, graphics and beyond. While approaches based on machine learning dominate modern 3D shape matching, almost all existing (learning-based) methods re
Externí odkaz:
http://arxiv.org/abs/2411.03511
Autor:
Weber, Mark, Yu, Lijun, Yu, Qihang, Deng, Xueqing, Shen, Xiaohui, Cremers, Daniel, Chen, Liang-Chieh
Masked transformer models for class-conditional image generation have become a compelling alternative to diffusion models. Typically comprising two stages - an initial VQGAN model for transitioning between latent space and image space, and a subseque
Externí odkaz:
http://arxiv.org/abs/2409.16211