Abstract:
We propose an end-to-end network that takes a single perspective RGB image of a complex road scene as input, to produce occlusion-reasoned layouts in perspective space as...Show MoreMetadata
Abstract:
We propose an end-to-end network that takes a single perspective RGB image of a complex road scene as input, to produce occlusion-reasoned layouts in perspective space as well as a parametric bird's-eye-view (BEV) space. In contrast to prior works that require dense supervision such as semantic labels in perspective view, our method only requires human annotations for parametric attributes that are cheaper and less ambiguous to obtain. To solve this challenging task, our design is comprised of modules that incorporate inductive biases to learn occlusion-reasoning, geometric transformation and semantic abstraction, where each module may be supervised by appropriately transforming the parametric annotations. We demonstrate how our design choices and proposed deep supervision help achieve meaningful representations and accurate predictions. We validate our approach on two public datasets, KITTI and NuScenes, to achieve state-of-the-art results with considerably less human supervision.
Date of Conference: 18-24 June 2022
Date Added to IEEE Xplore: 27 September 2022
ISBN Information:
ISSN Information:
Citations are not available for this document.
Cites in Papers - |
Cites in Papers - IEEE (2)
Select All
1.
Qi Song, Qingyong Hu, Chi Zhang, Yongquan Chen, Rui Huang, "Divide and Conquer: Improving Multi-Camera 3D Perception With 2D Semantic-Depth Priors and Input-Dependent Queries", IEEE Transactions on Image Processing, vol.33, pp.897-909, 2024.
2.
Hidetomo Sakaino, "DeepReject and DeepRoad: Road Condition Recognition and Classification Under Adversarial Conditions", 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA), pp.382-389, 2022.
Cites in Papers - Other Publishers (1)
1.
Jiayang Ao, Qiuhong Ke, Krista A. Ehinger, "Image amodal completion: A survey", Computer Vision and Image Understanding, vol.229, pp.103661, 2023.