Understanding RealWorld Indoor Scenes with Synthetic Data
| Autor: | Ankur Handa, Simon Stent, Vijay Badrinarayanan, Roberto Cipolla, Viorica Patraucean |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Training set
business.industry Computer science Supervised learning 020207 software engineering 02 engineering and technology Image segmentation computer.software_genre Machine learning Synthetic data Data modeling Set (abstract data type) Computer graphics 0202 electrical engineering electronic engineering information engineering Benchmark (computing) 020201 artificial intelligence & image processing Noise (video) Data mining Artificial intelligence business computer |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr.2016.442 |
| Popis: | Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments. Recent attempts with supervised learning have shown promise in this direction but also highlighted the need for enormous quantity of supervised data— performance increases in proportion to the amount of data used. However, this quickly becomes prohibitive when considering the manual labour needed to collect such data. In this work, we focus our attention on depth based semantic per-pixel labelling as a scene understanding problem and show the potential of computer graphics to generate virtually unlimited labelled data from synthetic 3D scenes. By carefully synthesizing training data with appropriate noise models we show comparable performance to state-of-theart RGBD systems on NYUv2 dataset despite using only depth data as input and set a benchmark on depth-based segmentation on SUN RGB-D dataset. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|