中文
相关论文

相关论文: Shape Representation using Gaussian Process mixtur…

200 篇论文

Recent advancements in photo-realistic novel view synthesis have been significantly driven by Gaussian Splatting (3DGS). Nevertheless, the explicit nature of 3DGS data entails considerable storage requirements, highlighting a pressing need…

计算机视觉与模式识别 · 计算机科学 2024-11-12 Minye Wu , Tinne Tuytelaars

We introduce Patchwork, a new general-purpose shape representation capable of modeling 2D and 3D geometry with a small number of parameters. Patchwork is grounded in a rigorous mathematical framework, providing provable complexity bounds…

图形学 · 计算机科学 2026-05-19 Ruichen Zheng , Biao Zhang , Michael Birsak , Mikhail Skopenkov , Peter Wonka

Three-dimensional point clouds provide highly accurate digital representations of objects, essential for applications in computer graphics, photogrammetry, computer vision, and robotics. However, comparing point clouds faces significant…

计算机视觉与模式识别 · 计算机科学 2025-12-19 Amit Vishwakarma , K. S. Subrahamanian Moosath

The goal of point set registration is to find point-by-point correspondences between point sets, each of which characterizes the shape of an object. Because local preservation of object geometry is assumed, prevalent algorithms in the area…

人工智能 · 计算机科学 2018-07-27 Osamu Hirose

Gaussian splatting, renowned for its exceptional rendering quality and efficiency, has emerged as a prominent technique in 3D scene representation. However, the substantial data volume of Gaussian splatting impedes its practical utility in…

计算机视觉与模式识别 · 计算机科学 2024-04-16 Xiangrui Liu , Xinju Wu , Pingping Zhang , Shiqi Wang , Zhu Li , Sam Kwong

Depth maps are widely used in feed-forward 3D Gaussian Splatting (3DGS) pipelines by unprojecting them into 3D point clouds for novel view synthesis. This approach offers advantages such as efficient training, the use of known camera poses,…

计算机视觉与模式识别 · 计算机科学 2025-06-06 Duochao Shi , Weijie Wang , Donny Y. Chen , Zeyu Zhang , Jia-Wang Bian , Bohan Zhuang , Chunhua Shen

Low-level 3D representations, such as point clouds, meshes, NeRFs and 3D Gaussians, are commonly used for modeling 3D objects and scenes. However, cognitive studies indicate that human perception operates at higher levels and interprets 3D…

计算机视觉与模式识别 · 计算机科学 2025-07-22 Zhirui Gao , Renjiao Yi , Yuhang Huang , Wei Chen , Chenyang Zhu , Kai Xu

We present GP-4DGS, a novel framework that integrates Gaussian Processes (GPs) into 4D Gaussian Splatting (4DGS) for principled probabilistic modeling of dynamic scenes. While existing 4DGS methods focus on deterministic reconstruction,…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Mijeong Kim , Jungtaek Kim , Bohyung Han

Open-vocabulary panoptic reconstruction is essential for advanced robotics perception and simulation. However, existing methods based on 3D Gaussian Splatting (3DGS) often struggle to simultaneously achieve geometric accuracy, coherent…

机器人学 · 计算机科学 2026-04-14 Xuan Yu , Yuxuan Xie , Changjian Jiang , Shichao Zhai , Rong Xiong , Yu Zhang , Yue Wang

Choosing the right representation for geometry is crucial for making 3D models compatible with existing applications. Focusing on piecewise-smooth man-made shapes, we propose a new representation that is usable in conventional CAD modeling…

图形学 · 计算机科学 2021-02-11 Dmitriy Smirnov , Mikhail Bessmeltsev , Justin Solomon

3D Gaussian Splatting (3DGS) has become the de facto method of 3D representation in many vision tasks. This calls for the 3D understanding directly in this representation space. To facilitate the research in this direction, we first build…

计算机视觉与模式识别 · 计算机科学 2025-09-09 Qi Ma , Yue Li , Bin Ren , Nicu Sebe , Ender Konukoglu , Theo Gevers , Luc Van Gool , Danda Pani Paudel

Learning a dense 3D model with fine-scale details from a single facial image is highly challenging and ill-posed. To address this problem, many approaches fit smooth geometries through facial prior while learning details as additional…

计算机视觉与模式识别 · 计算机科学 2022-03-21 Xingyu Ren , Alexandros Lattas , Baris Gecer , Jiankang Deng , Chao Ma , Xiaokang Yang , Stefanos Zafeiriou

Mapping with uncertainty representation is required in many research domains, especially for localization. Although there are many investigations regarding the uncertainty of the pose estimation of an ego-robot with map information, the…

机器人学 · 计算机科学 2023-08-30 Qianqian Zou , Claus Brenner , Monika Sester

Implicit surface representations, such as signed-distance functions, combined with deep learning have led to impressive models which can represent detailed shapes of objects with arbitrary topology. Since a continuous function is learned,…

计算机视觉与模式识别 · 计算机科学 2021-02-08 Edgar Tretschk , Ayush Tewari , Vladislav Golyanik , Michael Zollhöfer , Carsten Stoll , Christian Theobalt

In healthcare, accurately classifying medical images is vital, but conventional methods often hinge on medical data with a consistent grid structure, which may restrict their overall performance. Recent medical research has been focused on…

计算机视觉与模式识别 · 计算机科学 2023-06-06 Kishore Babu Nampalle , Pradeep Singh , Vivek Narayan Uppala , Sumit Gangwar , Rajesh Singh Negi , Balasubramanian Raman

With their meaningful geometry and their omnipresence in the 3D world, edges are extremely useful primitives in computer vision. 3D edges comprise of lines and curves, and methods to reconstruct them use either multi-view images or point…

计算机视觉与模式识别 · 计算机科学 2025-02-12 Kunal Chelani , Assia Benbihi , Torsten Sattler , Fredrik Kahl

This paper studies the problem of estimating physical properties (system identification) through visual observations. To facilitate geometry-aware guidance in physical property estimation, we introduce a novel hybrid framework that…

计算机视觉与模式识别 · 计算机科学 2024-11-01 Junhao Cai , Yuji Yang , Weihao Yuan , Yisheng He , Zilong Dong , Liefeng Bo , Hui Cheng , Qifeng Chen

As the most common representation for 3D shapes, mesh is often stored discretely with arrays of vertices and faces. However, 3D shapes in the real world are presented continuously. In this paper, we propose to learn a continuous…

计算机视觉与模式识别 · 计算机科学 2023-01-13 Zhongpai Gao

Many robotic tasks involving some form of 3D visual perception greatly benefit from a complete knowledge of the working environment. However, robots often have to tackle unstructured environments and their onboard visual sensors can only…

计算机视觉与模式识别 · 计算机科学 2022-10-24 Andrea Rosasco , Stefano Berti , Fabrizio Bottarel , Michele Colledanchise , Lorenzo Natale

3D Gaussian Splatting (3DGS) has shown remarkable success in synthesizing novel views given multiple views of a static scene. Yet, 3DGS faces challenges when applied to dynamic scenes because 3D Gaussian parameters need to be updated per…

图形学 · 计算机科学 2024-07-08 Kai Katsumata , Duc Minh Vo , Hideki Nakayama