基本情况
- 出处：Guizilini, V., Ambrus, R., Pillai, S., Raventos, A., & Gaidon, A. (2020). 3d packing for self-supervised monocular depth estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 2485-2494).
- Video: https://www.youtube.com/watch?v=b62iDkLgGSI
-
3D Packing for Self-Supervised Monocular Depth Estimation
-
Dataset: https://github.com/TRI-ML/DDAD
-
- Code: https://github.com/TRI-ML/packnet-sfm
尽管摄像头无处不在，但机器人平台通常依靠 LiDAR 等主动传感器进行直接 3D 感知。在这项工作中，我们提出了一种新的自监督单目深度估计方法，将几何与新的深度网络 PackNet 相结合，仅从未标记的单目视频中学习。我们的架构利用新颖的对称打包和解包块
