3D Gaussian Splatting在novel view synthesis中展现了令人印象深刻的效果；然而，它容易受到动态物体的影响，这些动态物体会污染原本静态场景的输入数据，即所谓的distractors。Distractors会对渲染质量产生严重影响，因为它们会被表示为视角相关效应或导致出现悬浮伪影。我们的目标是在3D Gaussian优化过程中识别并忽略这些distractors，以获得干净的重建。为此，我们采用一种自监督方法，在优化过程中观察图像残差，以确定可能被distractor伪造的区域。此外，我们利用预训练的分割网络提供物体感知能力，从而更准确地排除distractors。通过这种方式，我们获得了distractors的分割掩码，以在损失公式中有效地忽略它们。我们证明了我们的方法对各种distractors具有鲁棒性，并在受distractor污染的场景中显著提高了渲染质量，与3D Gaussian Splatting相比，PSNR提高了1.86dB。
英文摘要：
3D Gaussian Splatting has shown impressive novel view synthesis results; nonetheless, it is vulnerable to dynamic objects polluting the input data of an otherwise static scene, so called distractors. Distractors have severe impact on the rendering quality as they get represented as view-dependent effects or result in floating artifacts. Our goal is to identify and ignore such distractors during the 3D Gaussian optimization to obtain a clean reconstruction. To this end, we take a self-supervised approach that looks at the image residuals during the optimization to determine areas that have likely been falsified by a distractor. In addition, we leverage a pretrained segmentation network to provide object awareness, enabling more accurate exclusion of distractors. This way, we obtain segmentation masks of distractors to effectively ignore them in the loss formulation. We demonstrate that our approach is robust to various distractors and strongly improves rendering quality on distractor-polluted scenes, improving PSNR by 1.86dB compared to 3D Gaussian Splatting.
HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization
Sun Yat-sen University（中山大学）；Northeastern University（东北大学）；Guangdong Province Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China（教育部机器智能与先进计算重点实验室）
Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis
QUT Centre for Robotics, Australia（昆士兰大学机器人中心，澳大利亚）；ARIAM Hub, Australia（ARIAM中心，澳大利亚）；University of Wuppertal, Germany（乌尔姆大学，德国）；University of Osnabrück, Germany（奥斯纳布吕克大学，德国）
Geometry-Consistent 4D Gaussian Splatting for Sparse-Input Dynamic View Synthesis
The Hong Kong Polytechnic University, Hong Kong, China（香港理工大学）；Southern University of Science and Technology, Shenzhen, China（南方科技大学）；Indian Institute of Technology, Jodhpur, India（印度理工学院，朱道尔）；Institute of Cyberspace Technology, HKCT Institute of Higher Education, Hong Kong, China（网络空间技术研究所，香港高等教育学院）
Differentiable image sampling in the form of backward warping has seen broad adoption in tasks like depth estimation and optical flow prediction. In contrast, how to perform forward warping has seen less attention, partly due to additional challenges such as resolving the conflict of mapping multiple pixels to the same target location in a differentiable way. We propose softmax splatting to address this paradigm shift and show its effectiveness on the application of frame interpolation. Specifically, given two input frames, we forward-warp the frames and their feature pyramid representations b…
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）
GaussianEmoTalker: Real-Time Emotional Talking Head Synthesis with Audio-Driven and Blendshape-Based 3D Gaussian Splatting
PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院，教育部高维信息智能感知与系统重点实验室，PCA实验室）；Tsientang Institute for Advanced Study（浙江大学前沿交叉研究院）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）
