arXiv 2408.110852025-03-01cs.CV

GS-CPR：通过3D高斯泼溅实现高效的相机位姿优化

GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting

HKUST（香港科技大学）；University of Oxford（牛津大学）；Dartmouth College（达特茅斯学院）

Changkun Liu, Shuai Chen, Yash Bhalgat, Siyan Hu, Ming Cheng, Zirui Wang, Victor Adrian Prisacariu, Tristan Braud

备注：: Accepted to International Conference on Learning Representations (ICLR) 2025. During the ICLR review process, we changed the name of our framework from GSLoc to GS-CPR (Camera Pose Refinement), according to reviewers' comments. The project page is available at https://xrim-lab.github.io/GS-CPR/

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出基于3DGS的相机位姿优化框架GS-CPR，利用3DGS渲染图像和深度图建立2D-3D对应关系，并结合MASt3R模型与曝光自适应模块，在室内外视觉定位基准上实现了超越NeRF方法的准确性与运行效率。

摘要：

我们利用3D Gaussian Splatting (3DGS) 作为场景表示，并提出了一种新颖的测试时相机位姿优化 (CPR) 框架 GS-CPR。该框架提升了最先进的绝对位姿回归和场景坐标回归方法的定位精度。3DGS模型渲染高质量的合成图像和深度图，以促进2D-3D对应关系的建立。GS-CPR直接在RGB图像上运行，利用3D基础模型MASt3R进行精确的2D匹配，从而免除了训练特征提取器或描述符的需求。为了提高模型在具有挑战性的户外环境中的鲁棒性，我们在3DGS框架中引入了曝光自适应模块。因此，GS-CPR能够在给定单个RGB查询图像和粗略初始位姿估计的情况下，实现高效的一次性位姿优化。我们提出的方法在室内和室外视觉定位基准上的准确性和运行时间均超越了领先的基于NeRF的优化方法，并在两个室内数据集上实现了新的最先进精度。项目页面位于 https://xrim-lab.github.io/GS-CPR/。

英文摘要：

We leverage 3D Gaussian Splatting (3DGS) as a scene representation and propose a novel test-time camera pose refinement (CPR) framework, GS-CPR. This framework enhances the localization accuracy of state-of-the-art absolute pose regression and scene coordinate regression methods. The 3DGS model renders high-quality synthetic images and depth maps to facilitate the establishment of 2D-3D correspondences. GS-CPR obviates the need for training feature extractors or descriptors by operating directly on RGB images, utilizing the 3D foundation model, MASt3R, for precise 2D matching. To improve the robustness of our model in challenging outdoor environments, we incorporate an exposure-adaptive module within the 3DGS framework. Consequently, GS-CPR enables efficient one-shot pose refinement given a single RGB query and a coarse initial pose estimation. Our proposed approach surpasses leading NeRF-based optimization methods in both accuracy and runtime across indoor and outdoor visual localization benchmarks, achieving new state-of-the-art accuracy on two indoor datasets. The project page is available at https://xrim-lab.github.io/GS-CPR/.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。