.png){kind=icon}
返回
Learning to Simulate Complex Scenes for Street Scene Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2021.3062497.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Data simulation engines like Unity are becoming an increasingly important data source that allows us to acquire ground truth labels conveniently. Moreover, we can flexibly edit the content of an image in the engine, such as objects (position, orientation) and environments (illumination, occlusion). When using simulated data as training sets, its editable content can be leveraged to mimick the distribution of real-world data, and thus reduce the content difference between the synthetic and real domains. This paper explores content adaptation in the context of semantic segmentation, where the complex street scenes are fully synthesized using 19 classes of virtual objects from a first person driver perspective and controlled by 23 attributes. To optimize the attribute values and obtain a training set of similar content to real-world data, we propose a scalable discretization-and-relaxation (SDR) approach. Under a reinforcement learning framework, we formulate attribute optimization as a random-to-optimized mapping problem using a neural network. Our method has three characteristics. 1) Instead of editing attributes of individual objects, we focus on global attributes that have large influence on the scene structure, such as object density and illumination. 2) Attributes are quantized to discrete values, so as to reduce search space and training complexity. 3) Correlated attributes are jointly optimized in a group, so as to avoid meaningless scene structures and find better convergence points. Experiment shows our system can generate reasonable and useful scenes, from which we obtain promising real-world segmentation accuracy compared with existing synthetic training sets.
Keyword:
Engines
Lighting
Roads
Data models
Semantics
Buildings
Training
Content adaptation
data simulation
synthetic dataset search
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.7
论文数:
4.5K
被引数:
2.4W
机构
引用论文
Influence of duration of focal cerebral ischemia and neuronal nitric oxide synthase on translocation of apoptosis-inducing factor to the nucleus.png)
Neuroscience
OAAI
NeuroscienceIF0
OAAI分享收藏Determinants of quality of life in patients with fibromyalgia: A structural equation modeling approach纤维肌痛患者生活质量的决定因素: 结构方程建模方法PLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏Imagery, visual and tactual dimensions of imagery, and meaningfulness: Swedish norms for 858 nouns.
PREAI
分享收藏
查看更多内容