Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering
专题命中 Gaussian Splatting :Gaussian Splatting(abstract);分类 cs.CV
Comments Project page: https://city-super.github.io/scaffold-gs/
视觉与机器人
三维重建、NeRF、Gaussian Splatting、点云和空间智能。
专题命中 Gaussian Splatting :Gaussian Splatting(abstract);分类 cs.CV
Comments Project page: https://city-super.github.io/scaffold-gs/
专题命中 Gaussian Splatting :Gaussian Splatting(abstract);分类 cs.CV
Comments The link to our project website is https://control4darxiv.github.io
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.CV
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.CV
Comments Accepted by IEEE Transactions on Intelligent Vehicles
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.RO
Comments 8 pages, 4 figures. This paper has been accepted for publication in IEEE Robotics and Automation Letters. V2: Update weighting in (13), (28) and re-run results. Hypothesis, methodology, and general findings remain unchanged. Update Sec. II-A to reference IRLS, and update citation [11] accordingly. Include acknowledgement to Mitchell Cohen. V3: Update Section II-A to least-squares
Journal ref IEEE Robotics and Automation Letters, vol. 7, no. 3, pp. 7116-7123, 2022
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.CV
专题命中 Gaussian Splatting :3D reconstruction(abstract);分类 cs.CV
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.CV
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.RO
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.CV
Comments 11 pages, 5 figures
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.CV
Comments NeurIPS 2022
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.RO
Comments Accepted by IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.CV
Comments Published in AAAI Conference on Artificial Intelligence (2022)
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.RO
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.CV
Comments Published in WACV 2022
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.CV
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.RO
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.RO
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.CV
Comments Accepted by 3DV 2018. 9 pages. arXiv admin note: text overlap with arXiv:1707.08626
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.RO
Comments 8 pages, 6 figures, external contents (https://youtu.be/0-UlFRQT0JI)
Journal ref 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
专题命中 Gaussian Splatting :point cloud(abstract);分类 cs.RO
Comments Accepted for RSS 2017 Workshop on Spatial-Semantic Representations in Robotics
专题命中 Gaussian Splatting :spatial understanding(abstract);分类 cs.CV
Comments To appear in CVPR 2016
高斯混合模型之间的熵正则化部分最优传输与部分格罗莫夫-瓦瑟斯坦距离
专题命中 Gaussian Splatting :point cloud(abstract)
AI总结 本文针对高斯混合模型,开发熵正则化部分最优传输并定义部分混合格罗莫夫-瓦瑟斯坦距离,证明其极小值存在唯一性等性质,经数值实验验证该方法对异常值匹配具有鲁棒性。
Comments 7 figures
基于学习的三维高斯表示对结构化与非结构化体积的高效压缩
专题命中 Gaussian Splatting :novel view synthesis(abstract)
AI总结 提出基于三维高斯原语的显式模型压缩体积数据,通过加权聚合重建标量场,无需网格存储,在非结构化体积上全面超越隐式神经表示。
基于学习的无线电地图构建教程:数据、范式和物理感知
专题命中 Gaussian Splatting :Gaussian Splatting(abstract)
AI总结 本文系统综述了基于学习的无线电地图构建方法,从数据、范式和物理感知三个维度展开,并讨论了未来研究方向。
FLUIDSPLAT: 通过高斯原语从稀疏传感器重建物理场
机构 * Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) ; The Hong Kong University of Science and Technology(香港科学与技术大学) ; Mohamed bin Zayed University of Artificial Intelligence(莫扎德·本·扎耶德人工智能大学) ; Shanghai Jiaotong University(上海交通大学)
专题命中 Gaussian Splatting :Gaussian Splatting(abstract)
AI总结 提出FLUIDSPLAT模型,利用高斯原语作为空间显式中间表示,从稀疏传感器数据重建流场,理论分析了表示能力与观测数的关系,并在多个基准上实现误差降低11-28%。
Comments 24 pages, 5 figures,preprint
基于最近邻图的高维广义高斯分布 goodness-of-fit 非参数检验
专题命中 Gaussian Splatting :point cloud(abstract)
AI总结 本文提出基于最近邻图和适应性零原理的非参数检验方法,用于评估高维广义高斯分布模型的拟合优度,通过稳健标准化和交叉边计数实现,具有高维扩展性和几何解释。
Comments 22 pages, 5 pages
专题命中 Gaussian Splatting :point cloud(abstract)
无线环境建模的射频逆渲染
专题命中 Gaussian Splatting :Gaussian Splatting(abstract)
AI总结 本文提出一种物理基础的射频逆渲染框架,通过分离射频发射、几何和材料电磁特性,提升无线环境建模的精度与灵活性。
基于Sinkhorn的关联记忆检索使用球面Hellinger Kantorovich动力学
专题命中 Gaussian Splatting :point cloud(abstract)
AI总结 本文提出基于Sinkhorn的关联记忆检索方法,利用球面Hellinger Kantorovich动力学实现抗扰动恢复,通过几何收敛性和盆地不变性提升存储模式的稳定性与恢复能力。