arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

3D 视觉

三维重建、NeRF、Gaussian Splatting、点云和空间智能。

2026-01-28 至 2026-01-28 共收录 4 信号源:cs.CV, cs.GR, cs.RO

1. 点云 4 篇

2601.03660 2026-01-28 cs.CV 79%

MGPC: Multimodal Network for Generalizable Point Cloud Completion With Modality Dropout and Progressive Decoding

MGPC:多模态网络用于通用点云补全与模态丢弃和渐进解码

Jiangyuan Liu, Yuhao Zhao, Hongxuan Ma, Zhe Liu, Jian Wang, Wei Zou

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation of Chinese Academy of Sciences(中国科学院自动化研究所 multimodal 人工智能系统国家重点实验室) Chemical Defense Institute, Academy of Military Sciences(军事科学院化学防御研究院) Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation of Chinese Academy of Sciences(中国科学院自动化研究所 复杂系统认知与决策智能重点实验室)

专题命中 点云 :point cloud(title,abstract);分类 cs.CV

AI总结 MGPC通过多模态融合和渐进生成提升点云补全的泛化能力,构建大规模基准并验证其在现实场景中的有效性。

Comments Code and dataset are available at https://github.com/L-J-Yuan/MGPC

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.14859 2026-01-28 eess.IV 78%

Hint: hierarchical inter-frame correlation for one-shot point cloud sequence compression

提示:用于一次性点云序列压缩的分层帧间相关性

Yuchen Gao, Qi Zhang

专题命中 点云 :point cloud(title,abstract)

AI总结 HINT通过整合时间和空间相关性,实现了点云序列压缩的高效编码与解码,显著提升了压缩速度和比特率效率。

Comments This paper has been accepted at IEEE ICASSP 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.19228 2026-01-28 cs.CV 57%

Towards Pixel-Level VLM Perception via Simple Points Prediction

通过简单的点预测实现像素级VLM感知

Tianhui Song, Haoyu Lu, Hao Yang, Lin Sui, Haoning Wu, Zaida Zhou, Zhiqi Huang, Yiping Bao, Y. Charles, Xinyu Zhou, Limin Wang

专题命中 点云 :spatial understanding(abstract);分类 cs.CV

AI总结 SimpleSeg通过简单点预测实现多模态大语言模型的像素级感知,无需复杂架构即可获得高精度分割性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.17371 2026-01-28 cs.CG cs.GR cs.NA math.NA 57%

Robust Containment Queries over Collections of Rational Parametric Curves via Generalized Winding Numbers

通过广义环绕数实现对有理参数曲线集合的鲁棒包含查询

Jacob Spainhour, David Gunderman, Kenneth Weiss

专题命中 点云 :point cloud(abstract);分类 cs.GR

AI总结 本文提出了一种基于广义环绕数的鲁棒点包含查询方法,适用于有理参数曲线集合,提高了计算鲁棒性和性能。

Comments 14 pages, 18 figures

Journal ref ACM Transactions on Graphics (TOG), Volume 43, Issue 4, Pages 1 - 14 (2024)

详情

展开后加载摘要…

URL PDF HTML 收藏