KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera

By Shahram Izadi, David Kim, Otmar Hilliges, David Molyneaux, Richard A. Newcombe, Pushmeet Kohli, Jamie Shotton, Steve Hodges, Dustin Freeman, Andrew J. Davison and 1 more. 2011

2,576 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology, 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 Vision and Pattern Recognition

In Geology

In 3D Vision & Pose

Citations in the corpus

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language (2022, background): “…analogies to 3D vision and robotics, this can be thought of as building an on-thefly reconstruction of the sequence of events in the observable world with language, rather than other representations, such as dynamically-updated 3D meshes (Izadi et al. 2011) or neural fields (Tancik et al. 2022).”
Learning to Reconstruct Shapes from Unseen Classes (2018, background): “As handy depth sensors get mature [Izadi et al., 2011], and larger-scale RGB-D datasets become available [McCormac et al., 2017, Silberman et al., 2012, Song et al., 2017], many papers start to estimate depth [Chen et al., 2016, Eigen and Fergus, 2015], surface normals [Bansal and Russell, 2016,…”
Learning Shape Priors for Single-View 3D Completion and Reconstruction (2018, background): “With the development of depth sensors [23] and larger-scale RGB-D datasets [33, 42, 43], there have also been papers on estimating depth [6, 10], surface normals [1, 54], and other intrinsic images [25, 41] with deep networks.”
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling (2018, neutral): “With depth sensors like Kinect [24, 27], the community has built various RGB-D or depth-only datasets of objects and scenes.”
MarrNet: 3D Shape Reconstruction via 2.5D Sketches (2017, background): “With the development of depth sensors [Izadi et al., 2011] and larger scale RGB-D datasets [Silberman et al., 2012, Song et al., 2017, McCormac et al., 2017], there have also been papers on estimating depth [Chen et al., 2016, Eigen and Fergus, 2015], surface normals [Bansal and Russell, 2016, Wang…”
Cognitive Mapping and Planning for Visual Navigation (2017, background): “…studied in computer vision and robotics in the form of structure from motion and simultaneous localization and mapping (Fuentes-Pacheco et al. 2015; Izadi et al. 2011; Henry et al. 2010; Snavely et al. 2008) with a variety of sensing modalities such as range sensors, RGB cameras and RGB-D cameras.”
Real-Time 3D Reconstruction in Dynamic Scenes Using Point-Based Fusion (2013, methodology): “Recent online systems [6, 11] achieve high-quality results by adopting the volumetric fusion method of Curless and Levoy [2].”
Object Goal Navigation using Goal-Oriented Semantic Exploration (2020, background): “However, Active Neural SLAM, designed for maximizing exploration coverage, does not encode semantics in the episodic memory and thus does not learn semantic priors.”
Event-Based Moving Object Detection and Tracking (2018, methodology): “Our algorithm derives inspiration from 3D point cloud processing techniques, such as Kinect Fusion [11], which use warp fields to perform a global minimization on point clouds.”
Neural RGB-D Surface Reconstruction (2021, background): “While classical reconstruction methods [9, 33, 53] that purely rely on depth measurements struggle with the limitations of physical sen-”
Robobarista: Object Part Based Transfer of Manipulation Trajectories from Crowd-Sourcing in 3D Pointclouds (2015, methodology): “For each object, we took raw RGB-D images with the Microsoft Kinect sensor and stitched them using Kinect Fusion [20] to form a denser point-cloud in order to incorporate”
Space-time Neural Irradiance Fields for Free-Viewpoint Video (2020, background): “Examples include 3D reconstruction for static scenes [49, 27] or dynamic objects from a single [45, 26] or RGB-D cameras [14, 5, 26, 45, 73, 79].”
Very High Frame Rate Volumetric Integration of Depth Images on Mobile Devices (2015, methodology): “Volumetric representations have been established as a powerful method for computing dense, photorealistic 3D models from image observations [14, 8].”
Holoportation: Virtual 3D Teleportation in Real-time (2016, methodology): “We extract this information from a high ﬁdelity reconstruction of the user’s face obtained by aggregating frames using KinectFusion [23].”
Learning to Explore using Active Neural SLAM (2020, background): “While sparse reconstruction can be done well with monocular RGB images (Mur-Artal and Tardós, 2017), dense mapping is inefﬁcient (Newcombe et al., 2011) or requires specialized scanners such as Kinect (Izadi et al., 2011).”
Zero-shot Learning of 3D Point Cloud Objects (2019, background): “Nowadays, thanks to the availability of 3D depth cameras, obtaining 3D models of objects and environments are easier than before [2, 6].”