Efficiently reconstructing complex and intricate surfaces at scale is a long-standing goal in machine perception. To address this problem we introduce Deep Local Shapes (DeepLS), a deep shape representation that enables encoding and reconstruction of high-quality 3D shapes without prohibitive memory requirements. DeepLS replaces the dense volumetric signed distance function (SDF) representation used in traditional surface reconstruction systems with a set of locally learned continuous SDFs defined by a neural network, inspired by recent work such as DeepSDF. Unlike DeepSDF, which represents an object-level SDF with a neural network and a single latent code, we store a grid of independent latent codes, each responsible for storing information about surfaces in a small local neighborhood. This decomposition of scenes into local shapes simplifies the prior distribution that the network must learn, and also enables efficient inference. We demonstrate the effectiveness and generalization power of DeepLS by showing object shape encoding and reconstructions of full scenes, where DeepLS delivers high compression, accuracy, and local shape completion.
We present Gradient-SDF, a novel representation for 3D geometry that combines the advantages of implict and explicit representations. By storing at every voxel both the signed distance field as well as its gradient vector field, we enhance the capability of implicit representations with approaches originally formulated for explicit surfaces. As concrete examples, we show that (1) the Gradient-SDF allows us to perform direct SDF tracking from depth images, using efficient storage schemes like hash maps, and that (2) the Gradient-SDF representation enables us to perform photometric bundle adjust…
In this work, we present I$^2$-SDF, a new method for intrinsic indoor scene reconstruction and editing using differentiable Monte Carlo raytracing on neural signed distance fields (SDFs). Our holistic neural SDF-based framework jointly recovers the underlying shapes, incident radiance and materials from multi-view images. We introduce a novel bubble loss for fine-grained small objects and error-guided adaptive sampling scheme to largely improve the reconstruction quality on large-scale indoor scenes. Further, we propose to decompose the neural radiance field into spatially-varying material of …
We propose SDFDiff, a novel approach for image-based shape optimization using differentiable rendering of 3D shapes represented by signed distance functions (SDFs). Compared to other representations, SDFs have the advantage that they can represent shapes with arbitrary topology, and that they guarantee watertight surfaces. We apply our approach to the problem of multi-view 3D reconstruction, where we achieve high reconstruction quality and can capture complex topology of 3D objects. In addition, we employ a multi-resolution strategy to obtain a robust optimization algorithm. We further demonst…
Dense 3D object reconstruction from a single image has recently witnessed remarkable advances, but supervising neural networks with ground-truth 3D shapes is impractical due to the laborious process of creating paired image-shape datasets. Recent efforts have turned to learning 3D reconstruction without 3D supervision from RGB images with annotated 2D silhouettes, dramatically reducing the cost and effort of annotation. These techniques, however, remain impractical as they still require multi-view annotations of the same object instance during training. As a result, most experimental efforts t…
Accurate and Complete Surface Reconstruction from 3D Gaussians via Direct SDF Learning
Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University（航空工程系，香港理工大学）；Department of Computer Science and Technology, Nanjing University（计算机科学与技术系，南京大学）；School of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics（人工智能学院，南京航空航天大学）
GS-ROR$^2$: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstruction
VCIP, College of Computer Science, Nankai University（VCIP，计算机科学学院，南开大学）；School of Intelligence Science and Technology, Nanjing University（智能科学与技术学校，南京大学）
CASA-SDF: Curriculum-Aware Spatial Adaptation with Curvature-Guided Density for Neural Implicit Surface Reconstruction
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）；School of Automation, Nanjing University of Science and Technology（南京理工大学自动化学院）
By supervising camera rays between a scene and multi-view image planes, NeRF reconstructs a neural scene representation for the task of novel view synthesis. On the other hand, shadow rays between the light source and the scene have yet to be considered. Therefore, we propose a novel shadow ray supervision scheme that optimizes both the samples along the ray and the ray location. By supervising shadow rays, we successfully reconstruct a neural SDF of the scene from single-view images under multiple lighting conditions. Given single-view binary shadows, we train a neural network to reconstruct …
Scalable and High-Quality Neural Implicit Representation for 3D Reconstruction
School of Mathematical Sciences, University of Science and Technology of China（中国科学技术大学数学科学学院）；School of Computer Science and Informatics, Cardiff University（卡迪夫大学计算机科学与信息学院）
GS-Octree: Octree-based 3D Gaussian Splatting for Robust Object-level 3D Reconstruction Under Strong Lighting
College of Computing and Data Science（计算与数据科学学院）；Nanyang Technological University（南洋理工大学）；International School of Information Science & Engineering（信息科学与工程国际学院）；Dalian University of Technology（大连理工大学）；Institute of Software（软件研究所）；Chinese Academy of Sciences（中国科学院）；InnoPeak Technology, Inc.（InnoPeak科技公司）
GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；University of Science and Technology of China（中国科学技术大学）；Cornell University（康奈尔大学）
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
We present a StyleGAN2-based deep learning approach for 3D shape generation, called SDF-StyleGAN, with the aim of reducing visual and geometric dissimilarity between generated shapes and a shape collection. We extend StyleGAN2 to 3D generation and utilize the implicit signed distance function (SDF) as the 3D shape representation, and introduce two novel global and local shape discriminators that distinguish real and fake SDF values and gradients to significantly improve shape geometry and visual quality. We further complement the evaluation metrics of 3D generative models with the shading-imag…
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Adobe Research（奥多比研究院）；UC San Diego（加州大学圣地亚哥分校）；UC Berkeley（加州大学伯克利分校）
We present a method to automatically compute correct gradients with respect to geometric scene parameters in neural SDF renderers. Recent physically-based differentiable rendering techniques for meshes have used edge-sampling to handle discontinuities, particularly at object silhouettes, but SDFs do not have a simple parametric form amenable to sampling. Instead, our approach builds on area-sampling techniques and develops a continuous warping function for SDFs to account for these discontinuities. Our method leverages the distance to surface encoded in an SDF and uses quadrature on sphere tra…
University of Queensland（昆士兰大学）；Mila, University of Montreal（蒙特利尔大学米拉研究所）
Deep learning applied to the reconstruction of 3D shapes has seen growing interest. A popular approach to 3D reconstruction and generation in recent years has been the CNN encoder-decoder model usually applied in voxel space. However, this often scales very poorly with the resolution limiting the effectiveness of these models. Several sophisticated alternatives for decoding to 3D shapes have been proposed typically relying on complex deep learning architectures for the decoder model. In this work, we show that this additional complexity is not necessary, and that we can actually obtain high qu…
NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization
Simon Fraser University（西蒙菲莎大学）；University of British Columbia（不列颠哥伦比亚大学）；Amazon（亚马逊公司）；Changsha University of Science and Technology（长沙理工大学）；University of Toronto（多伦多大学）；Google DeepMind（谷歌DeepMind）
BayesFusion-SDF: Probabilistic Signed Distance Fusion with View Planning on CPU
Department of Computer Science and Business Systems（计算机科学与商业系统系）；Gargi Memorial Institute of Technology（加里纪念技术学院）；Computer and Informatics Group（计算机与信息组）；Variable Energy Cyclotron Centre（变能回旋加速器中心）；Engineering Sciences, Homi Bhabha National Institute Training School Complex（工程科学，霍米·巴布哈国家研究所培训学校复合体）
Tsinghua University（清华大学）；Wayne State University（韦恩州立大学）；University of Maryland, College Park（马里兰大学帕克分校）
Reconstructing continuous surfaces from 3D point clouds is a fundamental operation in 3D geometry processing. Several recent state-of-the-art methods address this problem using neural networks to learn signed distance functions (SDFs). In this paper, we introduce \textit{Neural-Pull}, a new approach that is simple and leads to high quality SDFs. Specifically, we train a neural network to pull query 3D locations to their closest points on the surface using the predicted signed distance values and the gradient at the query locations, both of which are computed by the network itself. The pulling …
Learning Scene-Level Signed Directional Distance Function with Ellipsoidal Priors and Neural Residuals
Department of Electrical and Computer Engineering, University of California San Diego（加州大学圣地亚哥分校电气与计算机工程系）；Brain Corporation（Brain公司）；Robotics Department, University of Michigan（密歇根大学机器人系）
UC San Diego（加州大学圣迭戈分校）；Johns Hopkins University（约翰斯·霍普金斯大学）
Recent work has made significant progress on using implicit functions, as a continuous representation for 3D rigid object shape reconstruction. However, much less effort has been devoted to modeling general articulated objects. Compared to rigid objects, articulated objects have higher degrees of freedom, which makes it hard to generalize to unseen shapes. To deal with the large shape variance, we introduce Articulated Signed Distance Functions (A-SDF) to represent articulated shapes with a disentangled latent space, where we have separate codes for encoding shape and articulation. We assume n…
Spinning LiDAR data are prevalent for 3D vision tasks. Since LiDAR data is presented in the form of point clouds, expensive 3D operations are usually required. This paper revisits spinning LiDAR scan formation and presents a cylindrical range image representation with a ray-wise projection/unprojection model. It is built upon raw scans and supports lossless conversion from 2D to 3D, allowing fast 2D operations, including 2D index-based neighbor search and downsampling. We then propose, to the best of our knowledge, the first multi-scale registration and dense signed distance function (SDF) rec…
State-of-the-art methods for large-scale 3D reconstruction from RGB-D sensors usually reduce drift in camera tracking by globally optimizing the estimated camera poses in real-time without simultaneously updating the reconstructed surface on pose changes. We propose an efficient on-the-fly surface correction method for globally consistent dense 3D reconstruction of large-scale scenes. Our approach uses a dense Visual RGB-D SLAM system that estimates the camera motion in real-time on a CPU and refines it in a global pose graph optimization. Consecutive RGB-D frames are locally fused into keyfra…
GSurf: Learning Signed Distance Fields from Splatting Opaque Gaussians for High-quality 3D Reconstruction
College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；School of Software, Dalian University of Technology（大连理工大学软件学院）
The University of Hong Kong（香港大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Texas A&M University（德州农工大学）
We present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs. Existing neural surface reconstruction approaches, such as DVR and IDR, require foreground mask as supervision, easily get trapped in local minima, and therefore struggle with the reconstruction of objects with severe self-occlusion or thin structures. Meanwhile, recent neural methods for novel view synthesis, such as NeRF and its variants, use volume rendering to produce a neural scene representation with robustness of optimization, even for high…
Tsinghua University（清华大学）；Wayne State University（韦恩州立大学）
It is vital to infer signed distance functions (SDFs) from 3D point clouds. The latest methods rely on generalizing the priors learned from large scale supervision. However, the learned priors do not generalize well to various geometric variations that are unseen during training, especially for extremely sparse point clouds. To resolve this issue, we present a neural network to directly infer SDFs from single sparse point clouds without using signed distance supervision, learned priors or even normals. Our insight here is to learn surface parameterization and SDFs inference in an end-to-end ma…
