3D Gaussian Splats (3DGS) have proven a versatile rendering primitive, both for inverse rendering as well as real-time exploration of scenes. In these applications, coherence across camera frames and multiple views is crucial, be it for robust convergence of a scene reconstruction or for artifact-free fly-throughs. Recent work started mitigating artifacts that break multi-view coherence, including popping artifacts due to inconsistent transparency sorting and perspective-correct outlines of (2D) splats. At the same time, real-time requirements forced such implementations to accept compromises in how transparency of large assemblies of 3D Gaussians is resolved, in turn breaking coherence in other ways. In our work, we aim at achieving maximum coherence, by rendering fully perspective-correct 3D Gaussians while using a high-quality approximation of accurate blending, hybrid transparency, on a per-pixel level, in order to retain real-time frame rates. Our fast and perspectively accurate approach for evaluation of 3D Gaussians does not require matrix inversions, thereby ensuring numerical stability and eliminating the need for special handling of degenerate splats, and the hybrid transparency formulation for blending maintains similar quality as fully resolved per-pixel transparencies at a fraction of the rendering costs. We further show that each of these two components can be independently integrated into Gaussian splatting systems. In combination, they achieve up to 2$\times$ higher frame rates, 2$\times$ faster optimization, and equal or better image quality with fewer rendering artifacts compared to traditional 3DGS on common benchmarks.
StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian Splatting
Google DeepMind（谷歌DeepMind）；University of British Columbia（不列颠哥伦比亚大学）；Google（谷歌）；Runway ML；Simon Fraser University（西蒙菲莎大学）；University of Toronto（多伦多大学）
3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene Reconstruction
Ontario Knowledge Intelligence Centre, Canada（加拿大安大略知识智能中心）；Canadian Institute of Interscience, Canada（加拿大跨学科科学研究所）；DeepCox Intelligence, Canada（加拿大DeepCox智能科技公司）
Endo-4DGX: Robust Endoscopic Scene Reconstruction and Illumination Correction with Gaussian Splatting
Department of Electronic Engineering, The Chinese University of Hong Kong (CUHK), Hong Kong SAR, China（香港中文大学电子工程系）；Shun Hing Institute of Advanced Engineering, CUHK, Hong Kong SAR, China（CUHK先进工程研究所）；City University of Hong Kong, Hong Kong, China（香港城市大学）；The University of Sydney, Sydney, NSW, Australia（悉尼大学）；Centre for Artificial Intelligence（人工智能中心）
USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting
School of Computer Science, Peking University（北京大学计算机科学学院）；State Key Laboratory for Multimedia Information Processing, Peking University（北京大学多媒体信息处理国家重点实验室）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）
DLO-Splatting: Tracking Deformable Linear Objects Using 3D Gaussian Splatting
Department of Aerospace Engineering and the Coordinated Science Laboratory at the University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校航空航天工程系及协调科学实验室）；Division of Robotics, Perception and Learning at KTH Royal Institute of Technology（皇家理工学院机器人、感知与学习 division）；NASA Ames Research Center（NASA阿姆斯研究中心）
Shanghai Innovation Institute（上海创新研究院）；OpenDriveLab；MMLab, The University of Hong Kong（香港大学 MMLab）；Technical University of Munich（慕尼黑工业大学）；Chalmers University of Technology（查尔姆斯理工大学）
Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
School of Computer Science；Engineering, State Key Laboratory of Complex Critical \& Software Environment, Jiangxi Research Institute, Beihang University；State Key Laboratory of Virtual Reality Technology；Macquarie University；Tohoku University；School of Computing, National University of Singapore
NRGS: Neural Regularization for Robust 3D Semantic Gaussian Splatting
Beijing University of Posts and Telecommunications, China（北京邮电大学，中国）；Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, China（北京多模态数据智能感知与治理重点实验室，中国）；The University of Osaka, Japan（大阪大学，日本）；Nankai University, China（南开大学，中国）
DreamScape: 3D Scene Creation via Gaussian Splatting joint Correlation Modeling
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；School of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Two-View Accumulation as the Primary Training Lever for Hybrid-Capture Gaussian Splatting: A Variance-Decomposition View of When Gradient Surgery Helps
The Hong Kong University of Science and Technology（香港科技大学）
PolarGS: Polarimetric Cues for Ambiguity-Free Gaussian Splatting with Accurate Geometry Recovery
Institute of Artificial Intelligence, Beihang University（北航人工智能研究院）；Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（北京未来区块链与隐私计算先进创新中心）；State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University（虚拟现实技术与系统国家重点实验室，北航计算机科学与工程学院）
