SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation

By Zechen Liu, Zizhang Wu, Roland Tóth. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020

470 citations recorded by the source corpus.

Estimating 3D orientation and translation of objects is essential for infrastructure-less autonomous navigation and driving. In case of monocular vision, successful methods have been mainly based on two ingredients: (i) a network generating 2D region proposals, (ii) a R-CNN structure predicting 3D object pose by utilizing the acquired regions of interest. We argue that the 2D detection network is redundant and introduces non-negligible noise for 3D detection. Hence, we propose a novel 3D object detection method, named SMOKE, in this paper that predicts a 3D bounding box for each detected object by combining a single keypoint estimate with regressed 3D variables. As a second contribution, we propose a multi-step disentangling approach for constructing the 3D bounding box, which significantly improves both training convergence and detection accuracy. In contrast to previous 3D detection techniques, our method does not require complicated pre/post-processing, extra data, and a refinement stage. Despite of its structural simplicity, our proposed SMOKE network outperforms all existing monocular 3D detection methods on the KITTI dataset, giving the best state-of-the-art result on both 3D object detection and Bird’s eye view evaluation. The code is available at https://github.com/lzccccc/SMOKE.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c0a640915e50983de7294a5127020695eaee30b9

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Is Pseudo-Lidar needed for Monocular 3D Object detection? (2021, background): “Simpler end-to-end monocular 3D detectors [3, 39] seem like a promising alternative, although they do not enjoy the same scalability beneﬁts of unsupervised pre-training due to their single stage nature.”
MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships (2020, result): “Very recently, several concurrent works [24, 21] also adopt a keypoint detection strategy similar to our work.”
Delving into Localization Errors for Monocular 3D Object Detection (2021, methodology): “SMOKE [23] can run faster than our method.”
DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries (2021, background): “Other works also explore advances in differentiable rendering [26] or 3D keypoint detection [27, 28, 1] to enable state-of-the-art 3D object detection performance.”
Objects are Different: Flexible Monocular 3D Object Detection (2021, methodology): “The penalty-reduced focal loss [26] is utilized for heatmap prediction as in [10, 25, 28].”
Categorical Depth Distribution Network for Monocular 3D Object Detection (2021, background): “For example, object keypoints can be estimated on the image plane, in order to assist in 3D box construction using known geometry [33, 29].”