The neural radiance fields (NeRF) have emerged as a prominent methodology for synthesizing realistic images of novel views. While neural radiance representations based on voxels or mesh individually offer distinct advantages, excelling in either rendering quality or speed, each has limitations in the other aspect. In response, we propose a hybrid representation named Vosh, seamlessly combining both voxel and mesh components in hybrid rendering for view synthesis. Vosh is meticulously crafted by optimizing the voxel grid based on neural rendering, strategically meshing a portion of the volumetric density field to surface. Therefore, it excels in fast rendering scenes with simple geometry and textures through its mesh component, while simultaneously enabling high-quality rendering in intricate regions by leveraging voxel component. The flexibility of Vosh is showcased through the ability to adjust hybrid ratios, providing users the ability to control the balance between rendering quality and speed based on flexible usage. Experimental results demonstrate that our method achieves commendable trade-off between rendering quality and speed, and notably has real-time performance on mobile devices. The interactive web demo and code are available at https://zyyzyy06.github.io/Vosh.
Deep generative models have shown success in generating 3D shapes with different representations. In this work, we propose Neural Volumetric Mesh Generator(NVMG) which can generate novel and high-quality volumetric meshes. Unlike the previous 3D generative model for point cloud, voxel, and implicit surface, the volumetric mesh representation is a ready-to-use representation in industry with details on both the surface and interior. Generating this such highly-structured data thus brings a significant challenge. We first propose a diffusion-based generative model to tackle this problem by gener…
Mesh reconstruction from a 3D point cloud is an important topic in the fields of computer graphic, computer vision, and multimedia analysis. In this paper, we propose a voxel structure-based mesh reconstruction framework. It provides the intrinsic metric to improve the accuracy of local region detection. Based on the detected local regions, an initial reconstructed mesh can be obtained. With the mesh optimization in our framework, the initial reconstructed mesh is optimized into an isotropic one with the important geometric features such as external and internal edges. The experimental results…
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Technical University of Munich（慕尼黑工业大学）；Cardiff University（卡迪夫大学）；Tencent AI Lab（腾讯人工智能实验室）
We present PVSeRF, a learning framework that reconstructs neural radiance fields from single-view RGB images, for novel view synthesis. Previous solutions, such as pixelNeRF, rely only on pixel-aligned features and suffer from feature ambiguity issues. As a result, they struggle with the disentanglement of geometry and appearance, leading to implausible geometries and blurry results. To address this challenge, we propose to incorporate explicit geometry reasoning and combine it with pixel-aligned features for radiance field prediction. Specifically, in addition to pixel-aligned features, we fu…
The University of Tokyo（东京大学）；RIKEN AIP（理化学研究所人工智能项目）；South China University of Technology（华南理工大学）；Alibaba Group（阿里巴巴集团）；Shenzhen Institute of Advanced Technology（深圳先进技术研究院）；Chinese Academy of Sciences（中国科学院）
Recently, Neural Radiance Fields (NeRF) is revolutionizing the task of novel view synthesis (NVS) for its superior performance. In this paper, we propose to synthesize dynamic scenes. Extending the methods for static scenes to dynamic scenes is not straightforward as both the scene geometry and appearance change over time, especially under monocular setup. Also, the existing dynamic NeRF methods generally require a lengthy per-scene training procedure, where multi-layer perceptrons (MLP) are fitted to model both motions and radiance. In this paper, built on top of the recent advances in voxel-…
Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surface
Imperial College London（伦敦帝国学院）；Tsinghua University（清华大学）；Meshy；Nanyang Technological University（南洋理工大学）；Mathmagic；The Chinese University of Hong Kong（香港中文大学）
VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesis
Technical University of Munich（慕尼黑工业大学）；Huawei Munich Research Center（华为慕尼黑研究中心）；Munich Center for Machine Learning（慕尼黑机器学习中心）；University of Stuttgart（斯图加特大学）；Karlsruhe University of Applied Sciences（卡尔斯鲁厄应用技术大学）
3D reconstruction is a core task in many applications such as robot navigation or sites inspections. Finding the best poses to capture part of the scene is one of the most challenging topic that goes under the name of Next Best View. Recently, many volumetric methods have been proposed; they choose the Next Best View by reasoning over a 3D voxelized space and by finding which pose minimizes the uncertainty decoded into the voxels. Such methods are effective, but they do not scale well since the underlaying representation requires a huge amount of memory. In this paper we propose a novel mesh-b…
The University of Tokyo（东京大学）；Preferred Networks, Inc.（Preferred Networks 公司）
We propose a new method for reconstructing controllable implicit 3D human models from sparse multi-view RGB videos. Our method defines the neural scene representation on the mesh surface points and signed distances from the surface of a human body mesh. We identify an indistinguishability issue that arises when a point in 3D space is mapped to its nearest surface point on a mesh for learning surface-aligned neural scene representation. To address this issue, we propose projecting a point onto a mesh surface using a barycentric interpolation with modified vertex normals. Experiments with the ZJ…
With the introduction of Neural Radiance Fields (NeRFs), novel view synthesis has recently made a big leap forward. At the core, NeRF proposes that each 3D point can emit radiance, allowing to conduct view synthesis using differentiable volumetric rendering. While neural radiance fields can accurately represent 3D scenes for computing the image rendering, 3D meshes are still the main scene representation supported by most computer graphics and simulation pipelines, enabling tasks such as real time rendering and physics-based simulations. Obtaining 3D meshes from neural radiance fields still re…
Representing 3D shape in deep learning frameworks in an accurate, efficient and compact manner still remains an open challenge. Most existing work addresses this issue by employing voxel-based representations. While these approaches benefit greatly from advances in computer vision by generalizing 2D convolutions to the 3D setting, they also have several considerable drawbacks. The computational complexity of voxel-encodings grows cubically with the resolution thus limiting such representations to low-resolution 3D reconstruction. In an attempt to solve this problem, point cloud representations…
University of Pennsylvania（宾夕法尼亚大学）；Amazon.com, Inc（亚马逊公司）
Human reconstruction and synthesis from monocular RGB videos is a challenging problem due to clothing, occlusion, texture discontinuities and sharpness, and framespecific pose changes. Many methods employ deferred rendering, NeRFs and implicit methods to represent clothed humans, on the premise that mesh-based representations cannot capture complex clothing and textures from RGB, silhouettes, and keypoints alone. We provide a counter viewpoint to this fundamental premise by optimizing a SMPL+D mesh and an efficient, multi-resolution texture representation using only RGB images, binary silhouet…
MeshSplatting: Differentiable Rendering with Opaque Meshes
University of Liège（里耶克斯大学）；Simon Fraser University（西蒙弗雷泽大学）；University of Maryland（马里兰大学）；University of British Columbia（不列颠哥伦比亚大学）；University of Toronto（多伦多大学）；Adobe Research（Adobe研究院）
With the emergence of neural radiance fields (NeRFs), view synthesis quality has reached an unprecedented level. Compared to traditional mesh-based assets, this volumetric representation is more powerful in expressing scene geometry but inevitably suffers from high rendering costs and can hardly be involved in further processes like editing, posing significant difficulties in combination with the existing graphics pipeline. In this paper, we present a hybrid volume-mesh representation, VMesh, which depicts an object with a textured mesh along with an auxiliary sparse volume. VMesh retains the …
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…
National Tsing Hua University（台湾清华大学）；ASUS AICS（华硕人工智能云端事业部）；Joint Research Center for AI Technology and All Vista Healthcare（人工智能技术与全瞻医疗联合研究中心）；Aeolus Robotics（Aeolus机器人公司）
We present a super-fast convergence approach to reconstructing the per-scene radiance field from a set of images that capture the scene with known poses. This task, which is often applied to novel view synthesis, is recently revolutionized by Neural Radiance Field (NeRF) for its state-of-the-art quality and flexibility. However, NeRF and its variants require a lengthy training time ranging from hours to days for a single scene. In contrast, our approach achieves NeRF-comparable quality and converges rapidly from scratch in less than 15 minutes with a single GPU. We adopt a representation consi…
NVIDIA（英伟达）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）
3D shape representations that accommodate learning-based 3D reconstruction are an open problem in machine learning and computer graphics. Previous work on neural 3D reconstruction demonstrated benefits, but also limitations, of point cloud, voxel, surface mesh, and implicit function representations. We introduce Deformable Tetrahedral Meshes (DefTet) as a particular parameterization that utilizes volumetric tetrahedral meshes for the reconstruction problem. Unlike existing volumetric approaches, DefTet optimizes for both vertex placement and occupancy, and is differentiable with respect to sta…
SPARF: Large-Scale Learning of 3D Sparse Radiance Fields from Few Input Images
Technical University of Munich (TUM)（慕尼黑工业大学（TUM））；King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学（KAUST））；University of Oxford（牛津大学）
Huazhong University of Science & Technology（华中科技大学）
Rendering moving human bodies at free viewpoints only from a monocular video is quite a challenging problem. The information is too sparse to model complicated human body structures and motions from both view and pose dimensions. Neural radiance fields (NeRF) have shown great power in novel view synthesis and have been applied to human body rendering. However, most current NeRF-based methods bear huge costs for both training and rendering, which impedes the wide applications in real-life scenarios. In this paper, we propose a rendering framework that can learn moving human body structures extr…
Hong Kong University of Science and Technology（香港科技大学）；Tencent Lightspeed & Quantum Studios（腾讯光子工作室群）；City University of Hong Kong（香港城市大学）
In recent years, sparse voxel-based methods have become the state-of-the-arts for 3D semantic segmentation of indoor scenes, thanks to the powerful 3D CNNs. Nevertheless, being oblivious to the underlying geometry, voxel-based methods suffer from ambiguous features on spatially close objects and struggle with handling complex and irregular geometries due to the lack of geodesic information. In view of this, we present Voxel-Mesh Network (VMNet), a novel 3D deep architecture that operates on the voxel and mesh representations leveraging both the Euclidean and geodesic information. Intuitively, …
3D shape analysis has been widely explored in the era of deep learning. Numerous models have been developed for various 3D data representation formats, e.g., MeshCNN for meshes, PointNet for point clouds and VoxNet for voxels. In this study, we present Representation-Agnostic Shape Fields (RASF), a generalizable and computation-efficient shape embedding module for 3D deep learning. RASF is implemented with a learnable 3D grid with multiple channels to store local geometry. Based on RASF, shape embeddings for various 3D shape representations (point clouds, meshes and voxels) are retrieved by co…
With the recent advances in hardware and rendering techniques, 3D models have emerged everywhere in our life. Yet creating 3D shapes is arduous and requires significant professional knowledge. Meanwhile, Deep learning has enabled high-quality 3D shape reconstruction from various sources, making it a viable approach to acquiring 3D shapes with minimal effort. Importantly, to be used in common 3D applications, the reconstructed shapes need to be represented as polygonal meshes, which is a challenge for neural networks due to the irregularity of mesh tessellations. In this survey, we provide a co…
TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA Reconstruction
Huazhong University of Science and Technology（华中科技大学）；Union Hospital, Tongji Medical College, Huazhong University of Science and Technology（华中科技大学同济医学院附属协和医院）
MeshDiffusion: Score-based Generative 3D Mesh Modeling
Mila（米拉人工智能研究所）；Université de Montréal（蒙特利尔大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ETH Zürich（苏黎世联邦理工学院）；McGill University（麦吉尔大学）；University of Cambridge（剑桥大学）
University of Tübingen（蒂宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Zhejiang University（浙江大学）
State-of-the-art 3D-aware generative models rely on coordinate-based MLPs to parameterize 3D radiance fields. While demonstrating impressive results, querying an MLP for every sample along each ray leads to slow rendering. Therefore, existing approaches often render low-resolution feature maps and process them with an upsampling network to obtain the final image. Albeit efficient, neural rendering often entangles viewpoint and content such that changing the camera pose results in unwanted changes of geometry or appearance. Motivated by recent results in voxel-based novel view synthesis, we inv…
TU Kaiserslautern（凯泽斯劳滕工业大学）；DFKI（德国人工智能研究中心）；NUST Pakistan（巴基斯坦国立科技大学）；UPM Saudi Arabia（沙特阿拉伯乌姆·库拉大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；Saarland Informatics Campus（萨尔兰信息学园区）
3D hand shape and pose estimation from a single depth map is a new and challenging computer vision problem with many applications. Existing methods addressing it directly regress hand meshes via 2D convolutional neural networks, which leads to artefacts due to perspective distortions in the images. To address the limitations of the existing methods, we develop HandVoxNet++, i.e., a voxel-based deep network with 3D and graph convolutions trained in a fully supervised manner. The input to our network is a 3D voxelized-depth-map-based on the truncated signed distance function (TSDF). HandVoxNet++…
TU Kaiserslautern（凯泽斯劳滕工业大学）；DFKI Kaiserslautern（德国人工智能研究中心凯泽斯劳滕分部）；NUST Pakistan（巴基斯坦国家科技大学）；UPM Saudi Arabia（沙特阿拉伯穆罕默德·本·法赫德王子大学）；MPII Saarland（马克斯·普朗克信息学研究所）
3D hand shape and pose estimation from a single depth map is a new and challenging computer vision problem with many applications. The state-of-the-art methods directly regress 3D hand meshes from 2D depth images via 2D convolutional neural networks, which leads to artefacts in the estimations due to perspective distortions in the images. In contrast, we propose a novel architecture with 3D convolutions trained in a weakly-supervised manner. The input to our method is a 3D voxelized depth map, and we rely on two hand shape representations. The first one is the 3D voxelized grid of the shape wh…
Middle East Technical University（中东技术大学）；Tohoku University（东北大学）；Koc University（科克大学）
We represent the sequence of fMRI (Functional Magnetic Resonance Imaging) brain volumes recorded during a cognitive stimulus by a graph which consists of a set of local meshes. The corresponding cognitive process, encoded in the brain, is then represented by these meshes each of which is estimated assuming a linear relationship among the voxel time series in a predefined locality. First, we define the concept of locality in two neighborhood systems, namely, the spatial and functional neighborhoods. Then, we construct spatially and functionally local meshes around each voxel, called seed voxel,…
Recently introduced implicit field representations offer an effective way of generating 3D object shapes. They leverage implicit decoder trained to take a 3D point coordinate concatenated with a shape encoding and to output a value which indicates whether the point is outside the shape or not. Although this approach enables efficient rendering of visually plausible objects, it has two significant limitations. First, it is based on a single neural network dedicated for all objects from a training set which results in a cumbersome training procedure and its application in real life. More importa…
