Semantic Pose using Deep Networks Trained on Synthetic RGB-D

no code implementations • ICCV 2015 • Jeremie Papon, Markus Schoeler

In this work we address the problem of indoor scene understanding from RGB-D images.

Scene Understanding Transfer Learning

Constrained Planar Cuts - Object Partitioning for Point Clouds

no code implementations • CVPR 2015 • Markus Schoeler, Jeremie Papon, Florentin Worgotter

We evaluate our algorithm on recordings from an RGB-D camera as well as the Princeton Segmentation Benchmark, using a fixed set of parameters across all object classes.

Clustering Object

Object Partitioning using Local Convexity

no code implementations • CVPR 2014 • Simon Christoph Stein, Markus Schoeler, Jeremie Papon, Florentin Worgotter

As an alternative to this, we present a new, efficient learning- and model-free approach for the segmentation of 3D point clouds into object parts.

Object Segmentation

Voxel Cloud Connectivity Segmentation - Supervoxels for Point Clouds

no code implementations • CVPR 2013 • Jeremie Papon, Alexey Abramov, Markus Schoeler, Florentin Worgotter

Unsupervised over-segmentation of an image into regions of perceptually similar pixels, known as superpixels, is a widely used preprocessing step in segmentation algorithms.

Object Segmentation +1