PRIMU: Uncertainty Estimation for Novel Views in Gaussian Splatting from Primitive-Based Representations of Error and Coverage
Department of Mathematics(数学系);University of Wuppertal(乌珀塔尔大学);Institute of Computer Science(计算机科学研究所);University of Osnabrück(奥斯纳布吕克大学);Centre for Robotics(机器人中心);Queensland University of Technology(昆士兰理工大学)
Thomas Gottwald, Edgar Heinert, Peter Stehr, Chamuditha Jayanga Galappaththige, Matthias Rottmann
备注:
Revised writing and figures; additional Gaussian Splatting experiments; added baselines and datasets; active view-selection experiments
We introduce Primitive-based Representations of Uncertainty (PRIMU), a post-hoc uncertainty estimation (UE) framework for Gaussian Splatting (GS). Reliable UE is essential for deploying GS in safety-critical domains such as robotics and medicine. Existing approaches typically estimate Gaussian-primitive variances and rely on the rendering process to obtain pixel-wise uncertainties. In contrast, we construct primitive-level representations of error and visibility/coverage from training views, capturing interpretable uncertainty information. These representations are obtained by projecting view-dependent training errors and coverage statistics onto the primitives. Uncertainties for novel views are inferred by rendering these primitive-level representations, producing uncertainty feature maps, which are aggregate through pixel-wise regression on holdout data. We analyze combinations of uncertainty feature maps and regression models to understand how their interactions affect prediction accuracy and generalization. PRIMU also enables an effective active view selection strategy by directly leveraging these uncertainty feature maps. Additionally, we study the effect of separating splatting into foreground and background regions. Our estimates show strong correlations with true errors, outperforming state-of-the-art methods, especially for depth UE and foreground objects. Finally, our regression models show generalization capabilities to unseen scenes, enabling UE without additional holdout data.
A Mixed-Primitive-based Gaussian Splatting Method for Surface Reconstruction
Lancaster University, United Kingdom(兰卡斯特大学,英国);The University of Queensland, Australia(昆士兰大学,澳大利亚);The Hong Kong Polytechnic University, China(香港理工大学,中国);University at Buffalo, United States of America(布法罗大学,美国)
SuperGaussians: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
The University of Hong Kong(香港大学);Shenzhen Graduate School of Peking University(北京大学深圳研究生院);Nanyang Technological University(南洋理工大学);Hong Kong University of Science and Technology(香港科技大学);Macau University of Science and Technology(澳门科技大学);Shandong University(山东大学);Texas A&M University(德克萨斯农工大学)
Denoising-GS: Gaussian Splatting with Spatial-aware Denoising
School of Computer Science and Artificial Intelligence(计算机科学与人工智能学院);Fudan University(复旦大学);Software of Engineering(软件工程系);Dalian University of Technology(大连理工大学);Department of Information Engineering(信息工程系);The Chinese University of Hong Kong(香港中文大学);College of Computing and Data Science(计算与数据科学学院);Nanyang Technological University(南洋理工大学)
NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting
Digital Future Lab, Flanders Make, Hasselt University(数字未来实验室,弗拉芒制造,哈塞尔特大学);Computer Graphics Lab, TU Braunschweig(计算机图形学实验室,图林根工业大学);Physics and Astronomy, University of New Mexico(物理与天文学,新墨西哥大学)
Hunan University(湖南大学);Nanyang Technological University(南洋理工大学);Lushan Innovation Lab(庐山创新实验室);Key Laboratory of Digital Culture Smart Design Technology, Minstry of Culture and Tourism(文化与旅游部数字文化智能设计技术重点实验室)
On the Geometric Accuracy of Implicit and Primitive-based Representations Derived from View Rendering Constraints
KU Leuven, Dept. Electrical Engineering, Research unit Processing Speech and Images(KU莱顿,电气工程系,语音与图像研究单位);UCLouvain, ICTEAM, Dept. Electrical Engineering(UCLouvain,ICTEAM,电气工程系);KU Leuven, Dept. Mechanical Engineering, Research unit Robotics, Automation and Mechatronics(KU莱顿,机械工程系,机器人、自动化与机电研究单位)
Swift4D:Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene
Shenzhen Graduate School, Peking University(北京大学深圳研究生院);Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology(广东省超高清沉浸式媒体技术重点实验室)