Real-time 3D reconstruction at scale using voxel hashing

By Matthias Nießner, Michael Zollhöfer, Shahram Izadi, Marc Stamminger. 2013

1,099 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes (2017, background): “The semantic seg-mentations are more than an order of magnitude larger than any previous RGB-D dataset.”
Volumetric and Multi-view CNNs for Object Classification on 3D Data (2016, methodology): “Real-world Reconstructions We provide a new realworld scanning dataset benchmark, comprising 243 objects of 12 categories; the geometry is captured with an ASUS Xtion Pro and a dense reconstruction is obtained using the publicly-available VoxelHashing framework [22].”
Deep Level Sets: Implicit Surface Representations for 3D Shape Inference (2019, methodology): “Convolutional neural networks [9,12,16,22,28] and generative adversarial models (GANs) [3, 24] have been successfully applied to 3D reconstruction problems by using either volumetric or point cloud representations.”
OctNetFusion: Learning Depth Fusion from Data (2017, methodology): “Large-scale 3D reconstruction has been achieved using iterative re-meshing [51] and efficient data structures [32, 46].”
Hierarchical Surface Prediction for 3D Object Reconstruction (2017, methodology): “Multi-view approaches alleviate this, by the use of data adaptive discretization of the volume with Delaunay tedrahedrization [20], voxel block hashing [25] or octrees [5], [31].”
Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis (2016, methodology): “Since the introduction of commodity range sensors such as the Microsoft Kinect, RGB-D scanning has gained a huge momentum in both ofﬂine and real-time contexts [26, 3, 28, 42, 4, 7].”
Matterport3D: Learning from RGB-D Data in Indoor Environments (2017, methodology): “In all, the dataset includes 90 buildings containing a total of 194,400 RGB-D images, 10,800 panorama, and 24,727,520 textured triangles; we provide textured mesh reconstructions obtained with [21] and [25].”
FPNN: Field Probing Neural Networks for 3D Data (2016, background): “it can be approximated by truncated distance fields [5], which is widely used in real time scanning and can be compactly stored by voxel hashing [21], 2.”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, neutral): “, points, voxels) to encode even a simple environment, such as an empty room (this issue can be partially mitigated by the socalled voxel hashing [188]).”
Deformable Shape Completion with Graph Convolutional Autoencoders (2017, background): “For static scenes, this problem was explored extensively, e.g., in [37, 38, 15].”
Efficient Surfel-Based SLAM using 3D Laser Range Data in Urban Environments (2018, background): “The surfel-based representation allows to model comparably large environments without a compromise in terms of reduced reconstruction fidelity due to reduced grid resolution or a more complex implementation [32, 19].”
Neural RGB-D Surface Reconstruction (2021, methodology): “While classical reconstruction methods [9, 33, 53] that purely rely on depth measurements struggle with the limitations of physical sen-”
3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions (2016, background): “Due to the importance of 3D reconstructions, there has been much research on designing algorithms and systems that can build high-fidelity reconstructions from RGB-D data [25, 26, 8].”
Learning to Navigate the Energy Landscape (2016, methodology): “The first capture is used to reconstruct a scene model, with reconstruction performed using the VoxelHashing framework of [32] in combination with global bundle adjustment.”
3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation (2018, methodology): “In 3D, the representation of a scene is typically obtained from RGB-D surface reconstruction methods [4,5,6,7] which often store scanned geometry in a 3D voxel grid where the surface is encoded by an implicit surface function such as a signed distance ﬁeld [8].”
Implicit Surface Representations As Layers in Neural Networks (2019, methodology): “Convolutional neural networks [9,12,16,22,29] and generative adversarial models (GANs) [3, 24] have been successfully applied to 3D reconstruction problems by using either volumetric or point cloud representations.”
OccuSeg: Occupancy-Aware 3D Instance Segmentation (2020, background): “The past ten years have witnessed a rapid development of real-time 3D reconstruction technologies [33, 34, 5, 47, 15] with the popularity of commercial RGB-D depth sensors like Kinect, Xtion, etc.”
VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction (2016, methodology): “Recently, the scene representation has been extended to scale to larger reconstruction volumes [3, 4, 30, 8, 5, 6].”