SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation – A Synthetic Dataset and Baselines

By Yuan-Ting Hu, Hong-Shuo Chen, Kexin Hui, Jia-Bin Huang, Alexander Gerhard Schwing. 2019

108 citations recorded by the source corpus.

We introduce SAIL-VOS (Semantic Amodal Instance Level Video Object Segmentation), a new dataset aiming to stimulate semantic amodal segmentation research. Humans can effortlessly recognize partially occluded objects and reliably estimate their spatial extent beyond the visible. However, few modern computer vision techniques are capable of reasoning about occluded parts of an object. This is partly due to the fact that very few image datasets and no video dataset exist which permit development of those methods. To address this issue, we present a synthetic dataset extracted from the photo-realistic game GTA-V. Each frame is accompanied with densely annotated, pixel-accurate visible and amodal segmentation masks with semantic labels. More than 1.8M objects are annotated resulting in 100 times more annotations than existing datasets. We demonstrate the challenges of the dataset by quantifying the performance of several baselines. Data and additional material is available at http://sailvos.web.illinois.edu.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Ziwei Liu
2. Chen Change Loy
3. Dahua Lin
4. Bo Dai
5. Xingang Pan
6. Xiaohang Zhan
7. Chi-Keung Tang
8. Lei Ke

In Computer Vision and Pattern Recognition

1. Chen Change Loy
2. Luc Van Gool
3. Ziwei Liu
4. Ming-Hsuan Yang
5. Dacheng Tao
6. Xiaogang Wang
7. Bo Dai
8. Trevor Darrell

Citations in the corpus

• CrDoCo: Pixel-Level Domain Transfer With Cross-Domain Consistency (2019, unknown): “Training the model on large-scale synthetic datasets has been extensively studied in semantic segmentation [41, 42, 15, 14, 7, 17, 34, 35, 53], multi-view stereo [18], depth estimation [48], optical flow [40, 19, 21], amodal segmentation [16], and object detection [7, 30].”
• Self-Supervised Scene De-Occlusion (2020, background): “Such ground truth can be obtained either from synthetic data [15, 16] or from manual annotations on real-world data [17, 18, 19], each of which with specific limitations.”
• Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers (2021, methodology): “COCOA cls [16] augments this dataset by assigning class-labels to the objects while SAIL-VOS dataset in [24] is targeted for video object segmentation.”