KinectFusion: Real-time dense surface mapping and tracking
- Richard A. Newcombe, S. Izadi, A. Fitzgibbon
- Computer Science10th IEEE International Symposium on Mixed and…
- 26 October 2011
We present a system for accurate real-time mapping of complex and arbitrary indoor scenes in variable lighting conditions, using only a moving low-cost depth camera and commodity graphics hardware.…
KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera
- S. Izadi, David Kim, A. Fitzgibbon
- PhysicsACM Symposium on User Interface Software and…
- 16 October 2011
Novel extensions to the core GPU pipeline demonstrate object segmentation and user interaction directly in front of the sensor, without degrading camera tracking or reconstruction, to enable real-time multi-touch interactions anywhere.
Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images
- J. Shotton, Ben Glocker, C. Zach, S. Izadi, A. Criminisi, A. Fitzgibbon
- Environmental Science, Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 1 June 2013
We address the problem of inferring the pose of an RGB-D camera relative to a known 3D scene, given only a single acquired image. Our approach employs a regression forest that is capable of inferring…
Real-time 3D reconstruction at scale using voxel hashing
- M. Nießner, M. Zollhöfer, S. Izadi, M. Stamminger
- Computer ScienceACM Transactions on Graphics
- 1 November 2013
An online system for large and fine scale volumetric reconstruction based on a memory and speed efficient data structure that compresses space, and allows for real-time access and updates of implicit surface data, without the need for a regular or hierarchical grid data structure.
SenseCam: A Retrospective Memory Aid
- Steve Hodges, Lyndsay Williams, K. Wood
- Computer ScienceUbiquitous Computing
- 17 September 2006
The results of this initial evaluation of the SenseCam are extremely promising; periodic review of images of events recorded by SenseCam results in significant recall of those events by the patient, which was previously impossible.
BundleFusion: real-time globally consistent 3D reconstruction using on-the-fly surface re-integration
- Angela Dai, M. Nießner, M. Zollhöfer, S. Izadi, C. Theobalt
- Computer ScienceTOGS
- 5 April 2016
This work systematically addresses issues with a novel, real-time, end-to-end reconstruction framework, which outperforms state-of-the-art online systems with quality on par to offline methods, but with unprecedented speed and scan completeness.
Real-Time 3D Reconstruction in Dynamic Scenes Using Point-Based Fusion
- M. Keller, D. Lefloch, M. Lambers, S. Izadi, T. Weyrich, A. Kolb
- Computer ScienceInternational Conference on 3D Vision
- 29 June 2013
A new system for real-time dense reconstruction with equivalent quality to existing online methods, but with support for additional spatial scale and robustness in dynamic scenes, designed around a simple and flat point-Based representation.
StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction
- S. Khamis, S. Fanello, Christoph Rhemann, Adarsh Kowdle, Julien P. C. Valentin, S. Izadi
- Computer ScienceEuropean Conference on Computer Vision
- 24 July 2018
This paper presents StereoNet, the first end-to-end deep architecture for real-time stereo matching that runs at 60fps on an NVidia Titan X, producing high-quality, edge-preserved, quantization-free…
Modeling Kinect Sensor Noise for Improved 3D Reconstruction and Tracking
- Chuong V. Nguyen, S. Izadi, David R. Lovell
- PhysicsSecond International Conference on 3D Imaging…
- 13 October 2012
The derived noise model can be used to filter Kinect depth maps for a variety of applications and applies to the KinectFusion system to extend filtering, volumetric fusion, and pose estimation within the pipeline.
Fusion4D: real-time performance capture of challenging scenes
- Mingsong Dou, S. Khamis, S. Izadi
- Computer ScienceACM Transactions on Graphics
- 11 July 2016
This work contributes a new pipeline for live multi-view performance capture, generating temporally coherent high-quality reconstructions in real-time, highly robust to both large frame-to-frame motion and topology changes, allowing us to reconstruct extremely challenging scenes.
...
...