Images

SYNTHIA (SYNTHetic Collection of Imagery and Annotations)

Introduced by Ros et al. in The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes

The SYNTHIA dataset is a synthetic dataset that consists of 9400 multi-viewpoint photo-realistic frames rendered from a virtual city and comes with pixel-level semantic annotations for 13 classes. Each frame has resolution of 1280 × 960.

Source: Orientation-aware Semantic Segmentation on Icosahedron Spheres

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Synthetic-to-Real Translation	SYNTHIA-to-Cityscapes	DCF
Domain Adaptation	SYNTHIA-to-Cityscapes	ILM-ASSL
Image-to-Image Translation	SYNTHIA-to-Cityscapes	HRDA + PiPa
Unsupervised Domain Adaptation	SYNTHIA-to-Cityscapes	DCF
Semantic Segmentation	SYNTHIA-to-Cityscapes	HRDA + PiPa
Image-to-Image Translation	SYNTHIA Fall-to-Winter	CyCADA
Semantic Segmentation	SYNTHIA-CVPR’16	SSMA
Semantic Segmentation	SYNTHIA	CGA-Net
Novel View Synthesis	Synthia Novel View Synthesis	Multi-view to Novel View
One-shot Unsupervised Domain Adaptation	SYNTHIA-to-Cityscapes	HRDA+DATUM