Search Results for author:
Found 12 papers, 4 papers with code
Learned Monocular Depth Priors in Visual-Inertial Initialization
Visual-inertial odometry (VIO) is the pose estimation backbone for most AR/VR and autonomous robotic systems today, in both academia and industry.
DepthLab: Real-Time 3D Interaction With Depth Maps for Mobile Augmented Reality
Slow adoption of depth information in the UX layer may be due to the complexity of processing depth data to simply render a mesh or detect interaction based on changes in the depth map.
Depth And Camera Motion
Indoor Monocular Depth Estimation
+1
HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching
Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not explicitly build a volume and instead relies on a fast multi-resolution initialization step, differentiable 2D geometric propagation and warping mechanisms to infer disparity hypotheses.
Ranked #3 on
Stereo Depth Estimation
on KITTI2015
(three pixel error metric)
Multimodal active speaker detection and virtual cinematography for video conferencing
Active speaker detection (ASD) and virtual cinematography (VC) can significantly improve the remote user experience of a video conference by automatically panning, tilting and zooming of a video conferencing camera: users subjectively rate an expert video cinematographer's video significantly higher than unedited video.
LookinGood: Enhancing Performance Capture with Real-time Neural Re-Rendering
We take the novel approach to augment such real-time performance capture systems with a deep architecture that takes a rendering from an arbitrary viewpoint, and jointly performs completion, super resolution, and denoising of the imagery in real-time.
StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction
A first estimate of the disparity is computed in a very low resolution cost volume, then hierarchically the model re-introduces high-frequency details through a learned upsampling function that uses compact pixel-to-pixel refinement networks.
Ranked #2 on
Stereo Depth Estimation
on sceneflow
ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems
In this paper we present ActiveStereoNet, the first deep learning solution for active stereo systems.
Low Compute and Fully Parallel Computer Vision With HashMatch
Numerous computer vision problems such as stereo depth estimation, object-class segmentation and foreground/background segmentation can be formulated as per-pixel image labeling tasks.
UltraStereo: Efficient Learning-Based Matching for Active Stereo Systems
Efficient estimation of depth from pairs of stereo images is one of the core problems in computer vision.
HyperDepth: Learning Depth From Structured Light Without Matching
We contribute an algorithm for solving this correspondence problem efficiently, without compromising depth accuracy.
Revisiting Depth Layers from Occlusions
We cast the problem of depth-layer segmentation as a discrete labeling problem on a spatiotemporal Markov Random Field (MRF) that uses the motion occlusion cues along with monocular cues and a smooth motion prior for the moving object.
Towards Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models
In many machine learning domains (such as scene understanding), several related sub-tasks (such as scene categorization, depth estimation, object detection) operate on the same raw data and provide correlated outputs.
