• Publications
  • Influence
Detailed 3D Representations for Object Recognition and Modeling
TLDR
In this paper, we revisit ideas from the early days of computer vision, namely, detailed, 3D geometric object class representations for recognition. Expand
Towards Scene Understanding with Detailed 3D Object Representations
TLDR
We propose to base scene understanding on a high-resolution object representation on a deformable 3D wireframe, which enables fine-grained modeling at the level of individual vertices and faces. Expand
Introducing SLAMBench, a performance and accuracy benchmarking methodology for SLAM
TLDR
We introduce SLAMBench, a publicly-available software framework which represents a starting point for quantitative, comparable and validatable experimental research to investigate trade-offs in performance, accuracy and energy consumption of a dense RGB-D SLAM system. Expand
Are Cars Just 3D Boxes? Jointly Estimating the 3D Shape of Multiple Objects
TLDR
In this paper, we approach the problem of scene understanding from the perspective of 3D shape modeling, and design a 3D scene representation that reasons jointly about the3D shape of multiple objects. Expand
Revisiting 3D geometric models for accurate object shape and pose
TLDR
We propose to revisit 3D geometric object class representations, providing object hypotheses with much more geometric detail than current object class detectors (see Fig. 1). Expand
Explicit Occlusion Modeling for 3D Object Class Representations
TLDR
In this paper, we tackle the challenge of modeling occlusion in the context of a 3D geometric object class model that is capable of fine-grained, part-level 3D object reconstruction. Expand
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing
TLDR
We present a deep convolutional neural network architecture to localize semantic parts in 2D image and 3D space while inferring their visibility states, given a single RGB image. Expand
Integrating algorithmic parameters into benchmarking and design space exploration in 3D scene understanding
TLDR
In this paper we investigate an emerging application, 3D scene understanding, likely to be significant in the mobile space in the near future. Expand
Comparative design space exploration of dense and semi-dense SLAM
TLDR
We extend the recently introduced SLAMBench framework to allow comparing two state-of-the-art SLAM pipelines, namely KinectFusion and LSD-SLAM, along the metrics of accuracy, energy consumption, and processing frame rate on two different hardware platforms. Expand
3D model selection from an internet database for robotic vision
TLDR
We propose a new method for automatically accessing an internet database of 3D models that are searchable only by their user-annotated labels, for using them for vision and robotic manipulation purposes. Expand
...
1
2
3
...