Opaque objects reconstructed by 3DGS often exhibit a falsely transparent surface, leading to inconsistent background and internal patterns under camera motion in interactive viewing. This issue stems from the ill-posed optimization in 3DGS. During training, background and foreground Gaussians are blended via alpha-compositing and optimized solely against the input RGB images using a photometric loss. As this process lacks an explicit constraint on surface opacity, the optimization may incorrectly assign transparency to opaque regions, resulting in view-inconsistent and falsely transparent. This issue is difficult to detect in standard evaluation settings but becomes particularly evident in object-centric reconstructions under interactive viewing. Although other causes of view-inconsistency have been explored recently, false transparency has not been explicitly identified. To the best of our knowledge, we are the first to identify, characterize, and develop solutions for this artifact, an underreported artifact in 3DGS. Our strategy, NGS, encourages surface Gaussians to adopt higher opacity by injecting opaque noise Gaussians in the object volume during training, requiring only minimal modifications to the existing splatting process. To quantitatively evaluate false transparency in static renderings, we propose a transmittance-based metric that measures the severity of this artifact. In addition, we introduce a customized, high-quality object-centric scan dataset exhibiting pronounced transparency issues, and we augment popular existing datasets with complementary infill noise specifically designed to assess the robustness of 3D reconstruction methods to false transparency. Experiments across multiple datasets show that NGS substantially reduces false transparency while maintaining competitive performance on standard rendering metrics, demonstrating its overall effectiveness.
Nix and Fix: Targeting 1000x Compression of 3D Gaussian Splatting with Diffusion Models
1 Chair of Media Technology, Munich Institute of Robotics；Machine Intelligence School of Computation, Information；Technology Technical University of Munich, 80333 Munich, Germany 2LTCI, T\'el\'ecom Paris, Institut Polytechnique de Paris, France
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）
Gaussian Splatting-based Low-Rank Tensor Representation for Multi-Dimensional Image Recovery
University of Electronic Science and Technology of China（电子科技大学）；Northwest Polytechnical University（西北工业大学）；Southern University of Science and Technology（南方科技大学）
Instant GaussianImage: A Generalizable and Self-Adaptive Image Representation via 2D Gaussian Splatting
School of Computer Science & Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；NERCGIS, China University of Geoscience (Wuhan)（中国地质大学（武汉）NERCGIS）；Department of Mathematics, University of South Carolina（南卡罗来纳大学数学系）
X$^{2}$-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction
The Chinese University of Hong Kong（香港中文大学）；Johns Hopkins University（约翰霍普金斯大学）；The Australian National University（澳大利亚国立大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior
ETH Zürich（苏黎世联邦理工学院）；Baidu Research（百度研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Harbin Institute of Technology（哈尔滨工业大学）；Tianjin University（天津大学）
