Search Results for author:
Found 11 papers, 2 papers with code
Discrete Optimization of Ray Potentials for Semantic 3D Reconstruction
The depth and semantic information is incorporated as a unary potential, smoothed by a pairwise regularizer.
From Point Clouds to Mesh Using Regression
Surface reconstruction from a point cloud is a standard subproblem in many algorithms for dense 3D reconstruction from RGB images or depth maps.
Matching neural paths: transfer from recognition to correspondence search
We propose to use a hierarchical semantic representation of the objects, coming from a convolutional neural network, to solve this ambiguity.
Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark
With the massive data set presented in this paper, we aim at closing this data gap to help unleash the full potential of deep learning methods for 3D labelling tasks.
Quad-networks: unsupervised learning to rank for interest point detection
In this paper, we ask a fundamental question: can we learn such detectors from scratch?
Semantic 3D Reconstruction with Continuous Regularization and Ray Potentials Using a Visibility Consistency Constraint
We propose an approach for dense semantic 3D reconstruction which uses a data term that is defined as potentials over viewing rays, combined with continuous surface area penalization.
Direction Matters: Depth Estimation With a Surface Normal Classifier
In this work we make use of recent advances in data driven classification to improve standard approaches for binocular stereo matching and single view depth estimation.
Pulling Things out of Perspective
The limitations of current state-of-the-art methods for single-view depth estimation and semantic segmentations are closely tied to the property of perspective geometry, that the perceived size of the objects scales inversely with the distance.
Human Pose Estimation Using a Joint Pixel-wise and Part-wise Formulation
Our goal is to detect humans and estimate their 2D pose in single images.
Learning Anchor Planes for Classification
It provides a set of anchor points which form a local coordinate system, such that each data point on the manifold can be approximated by a linear combination of its anchor points, and the linear weights become the local coordinate coding.
Efficient Minimization of Higher Order Submodular Functions using Monotonic Boolean Functions
E +n^4 {\log}^{O(1)} n)$ where $E$ is the time required to evaluate the function and $n$ is the number of variables \cite{Lee2015}.
