and|CVPR 2020 开源论文 | 多种可能性行人未来路径预测( 二 ) |future|Paths|ht

本文插图

▲ 我们提供了一个简单易用的场景可视化编辑工具
我们的新模型：The Multiverse Model
We propose a multi-decoder framework that predicts both coarse and fine locations of the person using scene semantic segmentation features.

本文插图

▲ The Multiverse Model for Multi-Future Trajectory Prediction

History Encoder computes representations from scene semantics
Coarse Location Decoder predicts multiple future grid location sequences by using beam search
Fine Location Decoder predicts exact future locations based on the grid predictions
Our model achieves STOA performance in the single-future trajectory prediction experiment and also the proposed multi-future trajectory prediction on the Forking Paths Dataset.

本文插图

▲ Single-Future Trajectory Prediction. The numbers are displacement errors and they are lower the better. For more details see [1].

本文插图

▲ Multi-Future Trajectory Prediction on the Forking Paths Dataset. The numbers are displacement errors and they are lower the better. For more details see [1].
Qualitative analysis with the popular Social-GAN [2] model:

本文插图

本文插图

▲ Qualitative comparison. The left column is from the Social-GAN [2] model. On the right it is our Multiverse model. The yellow trajectory is the observed trajectory and the green ones are the multi-future trajectory ground truth. The yellow-orange heatmaps are the model outputs.
回到前面的例子，你的预测对了吗？

本文插图

项目网站：
https://next.cs.cmu.edu/multiverse/
参考文献
[1] Liang, Junwei, Lu Jiang, Kevin Murphy, Ting Yu, and Alexander Hauptmann. “The garden of forking paths: Towards multi-future trajectory prediction.” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. [Dataset/Code/Model]
[2] Gupta, Agrim, Justin Johnson, Li Fei-Fei, Silvio Savarese, and Alexandre Alahi. “Social gan: Socially acceptable trajectories with generative adversarial networks.” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018.
[3] http://carla.org/
[4] https://github.com/JunweiLiang/Multiverse
? 稿件确系个人原创作品，来稿需注明作者个人信息（姓名+学校/工作单位+学历/职位+研究方向）
? PaperWeekly 默认每篇文章都是首发，均会添加“原创”标志