paper-with-me

SYNTHIA

SYNTHetic Collection of Imagery and Annotations

홈페이지 · 논문 538편

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 Image Source: https://synthia-dataset.net/

Images

벤치마크

Synthetic-to-Real Translation on SYNTHIA-to-Cityscapes 결과 114개

Image-to-Image Translation on SYNTHIA-to-Cityscapes 결과 84개

Unsupervised Domain Adaptation on SYNTHIA-to-Cityscapes 결과 46개

Domain Adaptation on SYNTHIA-to-Cityscapes 결과 33개

Semantic Segmentation on SYNTHIA-to-Cityscapes 결과 14개

Semantic Segmentation on SYNTHIA 결과 7개

Image-to-Image Translation on SYNTHIA Fall-to-Winter 결과 6개

Semantic Segmentation on SYNTHIA-CVPR’16 결과 4개

Source-Free Domain Adaptation on SYNTHIA-to-Cityscapes 결과 2개

Novel View Synthesis on Synthia Novel View Synthesis 결과 1개