Fetching the paper…

Reading the bibliography…

2018

Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing

Wrenninge, Magnus, Unger, Jonas

Original
PDF
Post on X

Understand

We introduce Synscapes -- a synthetic dataset for street scene parsing created using photorealistic rendering techniques, and show state-of-the-art results for training and validation as well as new types of analysis.

We study the behavior of networks trained on real data when performing inference on synthetic data: a key factor in determining the equivalence of simulation environments.
We also compare the behavior of networks trained on synthetic data and evaluated on real-world data.
Additionally, by analyzing pre-trained, existing segmentation and detection models, we illustrate how uncorrelated images along with a detailed set of annotations open up new avenues for analysis of computer vision systems, providing fine-grain information about how a model's performance changes according to factors such as distance, occlusion and relative object orientation.

Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing · Around

Built on

The rendering equation
1986
Earlier work this paper cites.
Are we ready for autonomous driving? the KITTI vision benchmark suite
2012
Earlier work this paper cites.
Vision meets robotics: The kitti dataset
2013
Earlier work this paper cites.
Faster r-cnn: Towards real-time object detection with region proposal networks
2015
Earlier work this paper cites.
The Cityscapes Dataset for Semantic Urban Scene Understanding
2016
Earlier work this paper cites.

Similar

Virtual worlds as proxy for multi-object tracking analysis
2016
Cited alongside, same era.
Playing for Data: Ground Truth from Computer Games
2016
Cited alongside, same era.
The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes
2016
Cited alongside, same era.
Multinet: Real-time joint semantic reasoning for autonomous driving
Original
2016
Cited alongside, same era.
Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
2017
Cited alongside, same era.

Then

Playing for benchmarks
2017
Later among the works it cites.
Procedural modeling and physically based rendering for synthetic data generation in automotive applications
Original
2017
Later among the works it cites.
Optimizing image acquisition systems for autonomous driving
2018
Closest in time.
Encoder-decoder with atrous separable convolution for semantic image segmentation
Original
2018
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…