Search Results - "Ren, Carl Yuheng"
-
1
Very High Frame Rate Volumetric Integration of Depth Images on Mobile Devices
Published in IEEE transactions on visualization and computer graphics (15-11-2015)“…Volumetric methods provide efficient, flexible and simple ways of integrating multiple depth images into a full 3D model. They provide dense and photorealistic…”
Get full text
Journal Article -
2
STAR3D: Simultaneous Tracking and Reconstruction of 3D Objects Using RGB-D Data
Published in 2013 IEEE International Conference on Computer Vision (01-12-2013)“…We introduce a probabilistic framework for simultaneous tracking and reconstruction of 3D rigid objects using an RGB-D camera. The tracking problem is handled…”
Get full text
Conference Proceeding Journal Article -
3
Regressing Local to Global Shape Properties for Online Segmentation and Tracking
Published in International journal of computer vision (01-02-2014)“…We propose a novel regression based framework that uses online learned shape information to reconstruct occluded object contours. Our key insight is to regress…”
Get full text
Journal Article -
4
-
5
3D Tracking of Multiple Objects with Identical Appearance Using RGB-D Input
Published in 2014 2nd International Conference on 3D Vision (01-12-2014)“…Most current approaches for 3D object tracking rely on distinctive object appearances. While several such trackers can be instantiated to track multiple…”
Get full text
Conference Proceeding -
6
Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception
Published 10-06-2023“…We introduce the Aria Digital Twin (ADT) - an egocentric dataset captured using Aria glasses with extensive object, environment, and human level ground truth…”
Get full text
Journal Article -
7
gSLICr: SLIC superpixels at over 250Hz
Published 14-09-2015“…We introduce a parallel GPU implementation of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Using a single graphic card, our…”
Get full text
Journal Article -
8
A Framework for the Volumetric Integration of Depth Images
Published 03-10-2014“…Volumetric models have become a popular representation for 3D scenes in recent years. One of the breakthroughs leading to their popularity was KinectFusion,…”
Get full text
Journal Article -
9
SemanticPaint: A Framework for the Interactive Segmentation of 3D Scenes
Published 13-10-2015“…We present an open-source, real-time implementation of SemanticPaint, a system for geometric reconstruction, object-class segmentation and learning of 3D…”
Get full text
Journal Article