• Publications
  • Influence
KinectFusion: Real-time dense surface mapping and tracking
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.
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
TLDR
This work introduces DeepSDF, a learned continuous Signed Distance Function (SDF) representation of a class of shapes that enables high quality shape representation, interpolation and completion from partial and noisy 3D input data.
KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera
TLDR
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.
DTAM: Dense tracking and mapping in real-time
TLDR
It is demonstrated that a dense model permits superior tracking performance under rapid motion compared to a state of the art method using features; and the additional usefulness of the dense model for real-time scene interaction in a physics-enhanced augmented reality application is shown.
DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time
TLDR
This work presents the first dense SLAM system capable of reconstructing non-rigidly deforming scenes in real-time, by fusing together RGBD scans captured from commodity sensors, and displays the updated model in real time.
The Replica Dataset: A Digital Replica of Indoor Spaces
TLDR
Replica, a dataset of 18 highly photo-realistic 3D indoor scene reconstructions at room and building scale, is introduced to enable machine learning (ML) research that relies on visually, geometrically, and semantically realistic generative models of the world.
SLAM++: Simultaneous Localisation and Mapping at the Level of Objects
TLDR
The object graph enables predictions for accurate ICP-based camera to model tracking at each live frame, and efficient active search for new objects in currently undescribed image regions, as well as the generation of an object level scene description with the potential to enable interaction.
Live dense reconstruction with a single moving camera
TLDR
This work takes point-based real-time structure from motion (SFM) as a starting point, generating accurate 3D camera pose estimates and a sparse point cloud and warp the base mesh into highly accurate depth maps based on view-predictive optical flow and a constrained scene flow update.
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction
TLDR
This work introduces Deep Local Shapes (DeepLS), a deep shape representation that enables encoding and reconstruction of high-quality 3D shapes without prohibitive memory requirements, and demonstrates the effectiveness and generalization power of this representation.
KinectFusion: real-time dynamic 3D surface reconstruction and interaction
We present KinectFusion, a system that takes live depth data from a moving Kinect camera and in real-time creates high-quality, geometrically accurate, 3D models. Our system allows a user holding a
...
...