3D高斯点划法（3DGS）实现了高效的渲染，但准确的表面重建仍面临挑战，因为几何监督不可靠。现有方法主要依赖基于深度的重投影来推断可见性并强制多视角一致性，导致根本性的循环依赖：可见性估计需要准确的深度，而深度监督本身依赖于可见性。在本文中，我们从可见性建模的角度重新审视多视角几何监督。而不是从像素级深度一致性推断可见性，我们显式地在高斯体层面建模可见性。我们引入了高斯可见性感知的多视角几何一致性（GVMV）公式，通过聚合共享高斯体的跨视角可见性，构建在共可见区域上的可靠监督。为进一步结合单目先验，我们提出了渐进式四叉树校准的深度对齐（QDC）策略，该策略在可见性感知指导下进行块级仿射校准，有效缓解尺度模糊问题，同时保留局部几何结构。在DTU和Tanks and Temples上的大量实验表明，我们的方法在重建精度上优于现有基于高斯的方法。我们的代码已完全开源，可在匿名仓库中获取：https://github.com/GVGScode/GVGS。
英文摘要：
3D Gaussian Splatting (3DGS) enables efficient rendering, yet accurate surface reconstruction remains challenging due to unreliable geometric supervision. Existing approaches predominantly rely on depth-based reprojection to infer visibility and enforce multi-view consistency, leading to a fundamental circular dependency: visibility estimation requires accurate depth, while depth supervision itself is conditioned on visibility. In this work, we revisit multi-view geometric supervision from the perspective of visibility modeling. Instead of inferring visibility from pixel-wise depth consistency, we explicitly model visibility at the level of Gaussian primitives. We introduce a Gaussian visibility-aware multi-view geometric consistency (GVMV) formulation, which aggregates cross-view visibility of shared Gaussians to construct reliable supervision over co-visible regions. To further incorporate monocular priors, we propose a progressive quadtree-calibrated depth alignment (QDC) strategy that performs block-wise affine calibration under visibility-aware guidance, effectively mitigating scale ambiguity while preserving local geometric structures. Extensive experiments on DTU and Tanks and Temples demonstrate that our method consistently improves reconstruction accuracy over prior Gaussian-based approaches. Our code is fully open-sourced and available at an anonymous repository: https://github.com/GVGScode/GVGS.
Univ Gustave Eiffel（古斯塔夫·埃菲尔大学）；IGN-ENSG（法国国立地理科学学院）；Ecole des Ponts（巴黎综合理工学院桥梁学校）；CNRS（法国国家科学研究中心）
Most current neural networks for reconstructing surfaces from point clouds ignore sensor poses and only operate on raw point locations. Sensor visibility, however, holds meaningful information regarding space occupancy and surface orientation. In this paper, we present two simple ways to augment raw point clouds with visibility information, so it can directly be leveraged by surface reconstruction networks with minimal adaptation. Our proposed modifications consistently improve the accuracy of generated surfaces as well as the generalization ability of the networks to unseen shape domains. Our…
The Ohio State University（俄亥俄州立大学）；Zhejiang University（浙江大学）；ETH Zürich（苏黎世联邦理工学院）
We present a novel framework for mesh reconstruction from unstructured point clouds by taking advantage of the learned visibility of the 3D points in the virtual views and traditional graph-cut based mesh generation. Specifically, we first propose a three-step network that explicitly employs depth completion for visibility prediction. Then the visibility information of multiple views is aggregated to generate a 3D mesh model by solving an optimization problem considering visibility in which a novel adaptive visibility weighting in surface determination is also introduced to suppress line of si…
We propose an approach for dense semantic 3D reconstruction which uses a data term that is defined as potentials over viewing rays, combined with continuous surface area penalization. Our formulation is a convex relaxation which we augment with a crucial non-convex constraint that ensures exact handling of visibility. To tackle the non-convex minimization problem, we propose a majorize-minimize type strategy which converges to a critical point. We demonstrate the benefits of using the non-convex constraint experimentally. For the geometry-only case, we set a new state of the art on two dataset…
In man-made environments such as indoor scenes, when point-based 3D reconstruction fails due to the lack of texture, lines can still be detected and used to support surfaces. We present a novel method for watertight piecewise-planar surface reconstruction from 3D line segments with visibility information. First, planes are extracted by a novel RANSAC approach for line segments that allows multiple shape support. Then, each 3D cell of a plane arrangement is labeled full or empty based on line attachment to planes, visibility and regularization. Experiments show the robustness to sparse input da…
Univ Gustave Eiffel（古斯塔夫·埃菲尔大学）；ENSG IGN（法国国立地理科学学院）；Ecole des Ponts（法国国立桥路学校）；CNRS（法国国家科学研究中心）
We introduce a novel learning-based, visibility-aware, surface reconstruction method for large-scale, defect-laden point clouds. Our approach can cope with the scale and variety of point cloud defects encountered in real-life Multi-View Stereo (MVS) acquisitions. Our method relies on a 3D Delaunay tetrahedralization whose cells are classified as inside or outside the surface by a graph neural network and an energy model solvable with a graph cut. Our model, making use of both local geometric attributes and line-of-sight visibility information, is able to learn a visibility model from a small a…
National Key Laboratory of Science and Technology on Multispectral Information Processing（多光谱信息处理国家重点实验室）；School of Artifical Intelligence and Automation（人工智能与自动化学院）；Huazhong University of Science and Technology（华中科技大学）
Recently, learning-based multi-view stereo methods have achieved promising results. However, they all overlook the visibility difference among different views, which leads to an indiscriminate multi-view similarity definition and greatly limits their performance on datasets with strong viewpoint variations. In this paper, a Pixelwise Visibility-aware multi-view Stereo Network (PVSNet) is proposed for robust dense 3D reconstruction. We present a pixelwise visibility network to learn the visibility information for different neighboring images before computing the multi-view similarity, and then …
Università degli Studi di Parma（帕尔马大学）；Vislab Srl（Vislab有限责任公司）；Ambarella Inc（安霸公司）
Image datasets have been steadily growing in size, harming the feasibility and efficiency of large-scale 3D reconstruction methods. In this paper, a novel approach for scaling Multi-View Stereo (MVS) algorithms up to arbitrarily large collections of images is proposed. Specifically, the problem of reconstructing the 3D model of an entire city is targeted, starting from a set of videos acquired by a moving vehicle equipped with several high-resolution cameras. Initially, the presented method exploits an approximately uniform distribution of poses and geometry and builds a set of overlapping clu…
LCPC（法国中央桥梁与道路实验室）；University Paris Est（巴黎东大学）；INRETS（法国国家交通与安全研究所）；Mines ParisTech（巴黎高科矿业学院）
Visibility distance on the road pathway plays a significant role in road safety and in particular, has a clear impact on the choice of speed limits. Visibility distance is thus of importance for road engineers and authorities. While visibility distance criteria are routinely taken into account in road design, only a few systems exist for estimating it on existing road networks. Most existing systems comprise a target vehicle followed at a constant distance by an observer vehicle, which only allows to check if a given, fixed visibility distance is available. We propose two new approaches that a…
Surfsvr: 2D Surface Priors as 3D Geometric Regularizers for Sparse Voxel Reconstruction
HIT (Shenzhen)（哈尔滨工业大学（深圳））；Tsinghua University（清华大学）；NWPU（西北工业大学）；Beijing Institute of Control and Engineering（北京控制与工程研究所）；Technical University of Munich（慕尼黑工业大学）
SplatGuide: Geometric Priors from 3D Gaussians for Pose-Free Novel View Synthesis
Aalto University（阿尔托大学）；Deep Render（深度渲染公司）；ELLIS Institute Finland（芬兰ELLIS研究所）；Nokia Technologies（诺基亚技术公司）；Tampere University（坦佩雷大学）；University of Oulu（奥卢大学）
ScenePlacer: Reformulating Scene-Level Object Pose Estimation as Visibility Field Learning
The Hong Kong University of Science and Technology（香港科技大学）；Shenzhen Loop Area Institute（深圳河套学院）；The University of Hong Kong（香港大学）；Tsinghua University（清华大学）
3D-USE: From Image-Level to Scene-Level Underwater Enhancement
College of Computer Science, Nankai University（南开大学计算机学院）；NKIARI（南开大学人工智能研究院（深圳））；School of Automation, Southeast University（东南大学自动化学院）；Advanced Ocean Institute of Southeast University, Nantong（东南大学南通先进海洋研究院）
DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments
The University of Tokyo（东京大学）；Nanjing University of Science and Technology（南京理工大学）；Dalian Maritime University（大连海事大学）；Shanghai Astronomical Observatory（上海天文台）；University of Chinese Academy of Sciences（中国科学院大学）；Dalian University of Technology（大连理工大学）
VAD-GS: Visibility-Aware Densification for 3D Gaussian Splatting in Dynamic Urban Scenes
Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（同济大学智能自主系统研究所）；College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University（西安交通大学人机混合增强智能国家实验室）
We present an out-of-core variational approach for surface reconstruction from a set of aligned depth maps. Input depth maps are supposed to be reconstructed from regular photos or/and can be a representation of terrestrial LIDAR point clouds. Our approach is based on surface reconstruction via total generalized variation minimization ($TGV$) because of its strong visibility-based noise-filtering properties and GPU-friendliness. Our main contribution is an out-of-core OpenCL-accelerated adaptation of this numerical algorithm which can handle arbitrarily large real-world scenes with scale diver…
Dense semantic 3D reconstruction is typically formulated as a discrete or continuous problem over label assignments in a voxel grid, combining semantic and depth likelihoods in a Markov Random Field framework. The depth and semantic information is incorporated as a unary potential, smoothed by a pairwise regularizer. However, modelling likelihoods as a unary potential does not model the problem correctly leading to various undesirable visibility artifacts. We propose to formulate an optimization problem that directly optimizes the reprojection error of the 3D model with respect to the image es…
KTH Royal Institute of Technology（瑞典皇家理工学院）；Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague（布拉格捷克理工大学捷克信息学、机器人与控制论研究所）；Georgia Tech（佐治亚理工学院）
We present a complete classification of all minimal problems for generic arrangements of points and lines completely observed by calibrated perspective cameras. We show that there are only 30 minimal problems in total, no problems exist for more than 6 cameras, for more than 5 points, and for more than 6 lines. We present a sequence of tests for detecting minimality starting with counting degrees of freedom and ending with full symbolic and numeric verification of representative examples. For all minimal problems discovered, we present their algebraic degrees, i.e. the number of solutions, whi…
RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction
IRIT, UMR CNRS 5505（法国国家科学研究中心IRIT联合研究单位）；Normandie Univ, UNICAEN, ENSICAEN, CNRS, GREYC（诺曼底大学、卡昂大学、卡昂高等工程师学院、法国国家科学研究中心GREYC联合研究单位）；Balgrist Hospital, University of Zurich（苏黎世大学巴尔格里斯医院）；OR-X
Recent work on the intrinsic image of humans starts to consider the visibility of incident illumination and encodes the light transfer function by spherical harmonics. In this paper, we show that such a light transfer function can be further decomposed into visibility and cosine terms related to surface normal. Such decomposition allows us to recover the surface normal in addition to visibility. We propose a deep learning-based approach with a reconstruction loss for training on real-world images. Results show that compared with previous works, the reconstruction of human face from our method …
Sat-DN: Implicit Surface Reconstruction from Multi-View Satellite Images with Depth and Normal Supervision
School of Remote Sensing Information Engineering, Wuhan University（遥感信息工程学院，武汉大学）；State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University（测绘遥感信息工程国家重点实验室，武汉大学）
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
Insta360 Research（Insta360研究机构）；Sun Yat-sen University（中山大学）；South China University of Technology（华南理工大学）；University of Chinese Academy of Sciences（中国科学院大学）；Harbin Engineering University（哈尔滨工程大学）；Wuhan University（武汉大学）
Neural Tree Reconstruction for the Open Forest Observatory
Berkeley AI Research, University of California, Berkeley（加州大学伯克利分校伯克利人工智能研究）；Department of Plant Sciences, University of California, Davis（加州大学戴维斯分校植物科学系）
Hong Kong University of Science and Technology（香港科技大学）；Everest Innovation Technology（珠峰创新科技）
Current bundle adjustment solvers such as the Levenberg-Marquardt (LM) algorithm are limited by the bottleneck in solving the Reduced Camera System (RCS) whose dimension is proportional to the camera number. When the problem is scaled up, this step is neither efficient in computation nor manageable for a single compute node. In this work, we propose a stochastic bundle adjustment algorithm which seeks to decompose the RCS approximately inside the LM iterations to improve the efficiency and scalability. It first reformulates the quadratic programming problem of an LM iteration based on the clus…
University of Florida（佛罗里达大学）；Microsoft Research（微软研究院）
Many 3D vision systems localize cameras within a scene using 3D point clouds. Such point clouds are often obtained using structure from motion (SfM), after which the images are discarded to preserve privacy. In this paper, we show, for the first time, that such point clouds retain enough information to reveal scene appearance and compromise privacy. We present a privacy attack that reconstructs color images of the scene from the point cloud. Our method is based on a cascaded U-Net that takes as input, a 2D multichannel image of the points rendered from a specific viewpoint containing point dep…
We present a complete classification of minimal problems for generic arrangements of points and lines in space observed partially by three calibrated perspective cameras when each line is incident to at most one point. This is a large class of interesting minimal problems that allows missing observations in images due to occlusions and missed detections. There is an infinite number of such minimal problems; however, we show that they can be reduced to 140616 equivalence classes by removing superfluous features and relabeling the cameras. We also introduce camera-minimal problems, which are pra…
