English
Related papers

Related papers: G2P: Gaussian-to-Point Attribute Alignment for Bou…

200 papers

Recently, immersive media and autonomous driving applications have significantly advanced through 3D Gaussian Splatting (3DGS), which offers high-fidelity rendering and computational efficiency. Despite these advantages, 3DGS as a…

Graphics · Computer Science 2025-05-27 Kangli Wang , Shihao Li , Qianxi Yi , Wei Gao

The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Peizhen Zheng , Dongjing Jiang , Qingchong Jiao , Redouane EL Bouchtaoui , Flynnwell Jianfei Zhang

Gaussian Splatting has become the method of choice for 3D reconstruction and real-time rendering of captured real scenes. However, fine appearance details need to be represented as a large number of small Gaussian primitives, which can be…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Panagiotis Papantonakis , Georgios Kopanas , Fredo Durand , George Drettakis

The deficiency of 3D segmentation labels is one of the main obstacles to effective point cloud segmentation, especially for scenes in the wild with varieties of different objects. To alleviate this issue, we propose a novel deep graph…

Computer Vision and Pattern Recognition · Computer Science 2020-05-19 Haiyan Wang , Xuejian Rong , Liang Yang , Jinglun Feng , Jizhong Xiao , Yingli Tian

Recently, 3D Gaussian Splatting (3D-GS) has achieved significant success in real-time, high-quality 3D scene rendering. However, it faces several challenges, including Gaussian redundancy, limited ability to capture view-dependent effects,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-16 Junxi Jin , Xiulai Li , Haiping Huang , Lianjun Liu , Yujie Sun , Logan Liu

The semantic synthesis of unseen scenes from multiple viewpoints is crucial for research in 3D scene understanding. Current methods are capable of rendering novel-view images and semantic maps by reconstructing generalizable Neural Radiance…

Graphics · Computer Science 2025-05-09 Feng Xiao , Hongbin Xu , Wanlin Liang , Wenxiong Kang

In the task of 3D Aerial-view Scene Semantic Segmentation (3D-AVS-SS), traditional methods struggle to address semantic ambiguity caused by scale variations and structural occlusions in aerial images. This limits their segmentation accuracy…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Xu Tang , Junan Jia , Yijing Wang , Jingjing Ma , Xiangrong Zhang

Bridging 2D and 3D sensor modalities is critical for robust perception in autonomous systems. However, image-to-point cloud (I2P) registration remains challenging due to the semantic-geometric gap between texture-rich but depth-ambiguous…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Xingmei Wang , Xiaoyu Hu , Chengkai Huang , Ziyan Zeng , Guohao Nie , Quan Z. Sheng , Lina Yao

3D Gaussian Splatting (3DGS) provides an explicit and efficient scene representation, but its primitives lack inherent object-level identity, hindering downstream tasks such as open-vocabulary scene understanding. Existing methods typically…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Guiyu Liu , Niklas Vaara , Janne Mustaniemi , Juho Kannala , Janne Heikkilä

Gaussian Splatting has revolutionized the world of novel view synthesis by achieving high rendering performance in real-time. Recently, studies have focused on enriching these 3D representations with semantic information for downstream…

Computer Vision and Pattern Recognition · Computer Science 2024-09-02 Mihnea-Bogdan Jurca , Remco Royen , Ion Giosan , Adrian Munteanu

3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale annotation.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Hongbin Lin , Yifan Jiang , Juangui Xu , Jesse Jiaxi Xu , Yi Lu , Zhengyu Hu , Ying-Cong Chen , Hao Wang

Point cloud registration sits at the core of many important and challenging 3D perception problems including autonomous navigation, SLAM, object/scene recognition, and augmented reality. In this paper, we present a new registration…

Computer Vision and Pattern Recognition · Computer Science 2018-07-10 Ben Eckart , Kihwan Kim , Jan Kautz

Current point cloud registration methods are mainly based on local geometric information and usually ignore the semantic information contained in the scenes. In this paper, we treat the point cloud registration problem as a semantic…

Computer Vision and Pattern Recognition · Computer Science 2023-10-19 Shaocong Liu , Tao Wang , Yan Zhang , Ruqin Zhou , Li Li , Chenguang Dai , Yongsheng Zhang , Longguang Wang , Hanyun Wang

Rendering high-fidelity images from sparse point clouds is still challenging. Existing learning-based approaches suffer from either hole artifacts, missing details, or expensive computations. In this paper, we propose a novel framework to…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Jiaxu Wang , Ziyi Zhang , Junhao He , Renjing Xu

Visual localization is the task of estimating a 6-DoF camera pose of a query image within a provided 3D reference map. Thanks to recent advances in various 3D sensors, 3D point clouds are becoming a more accurate and affordable option for…

Computer Vision and Pattern Recognition · Computer Science 2023-09-15 Minjung Kim , Junseo Koo , Gunhee Kim

Point clouds produced by 3D sensors are often sparse and noisy, posing challenges for tasks requiring dense and high-fidelity 3D representations. Prior work has explored both implicit feature-based upsampling and distance-function learning…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Mahmoud Khater , Mona Strauss , Philipp von Olshausen , Alexander Reiterer

Image-to-point-cloud registration (I2P) is a fundamental task in robotic applications such as manipulation,grasping, and localization. Existing deep learning-based I2P methods seek to align image and point cloud features in a learned…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Muyao Peng , Shun Zou , Pei An , You Yang , Qiong Liu

Geometry and color information provided by the point clouds are both crucial for 3D scene understanding. Two pieces of information characterize the different aspects of point clouds, but existing methods lack an elaborate design for the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-02 Guofan Fan , Zekun Qi , Wenkai Shi , Kaisheng Ma

Point cloud semantic segmentation plays an essential role in autonomous driving, providing vital information about drivable surfaces and nearby objects that can aid higher level tasks such as path planning and collision avoidance. While…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Ozan Unal , Luc Van Gool , Dengxin Dai

Estimation of differential geometric quantities in discrete 3D data representations is one of the crucial steps in the geometry processing pipeline. Specifically, estimating normals and sharp feature lines from raw point cloud helps improve…

Computer Vision and Pattern Recognition · Computer Science 2020-08-07 Albert Matveev , Alexey Artemov , Denis Zorin , Evgeny Burnaev