Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving

Chen, Y.-N., Dai, H. and Ding, Y. (2022) Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 18-24 Jun 2022, pp. 877-887. ISBN 9781665469463 (doi: 10.1109/CVPR52688.2022.00096)

Full text not currently available from Enlighten.

Publisher's URL:


Pseudo-LiDAR 3D detectors have made remarkable progress in monocular 3D detection by enhancing the capability of perceiving depth with depth estimation networks, and using LiDAR-based 3D detection architectures. The Advanced stereo 3D detectors can also accurately localize 3D objects. The gap in image-to-image generation for stereo views is much smaller than that in image-to-LiDAR generation. Motivated by this, we propose a Pseudo-Stereo 3D detection framework with three novel virtual view generation methods, including image-level generation, feature-level generation, and feature-clone, for detecting 3D objects from a single image. Our analysis of depth-aware learning shows that the depth loss is effective in only feature-level virtual view generation and the estimated depth map is effective in both image-level and feature-level in our framework. We propose a disparity-wise dynamic convolution with dynamic kernels sampled from the disparity feature map to filter the features adaptively from a single image for generating virtual image features, which eases the feature degradation caused by the depth estimation errors. Till submission (November 18, 2021), our Pseudo-Stereo 3D detection framework ranks 1 st on car, pedestrian, and cyclist among the monocular 3D detectors with publications on the KITTI-3D benchmark. The code is released at

Item Type:Conference Proceedings
Glasgow Author(s) Enlighten ID:Dai, Dr Hang
Authors: Chen, Y.-N., Dai, H., and Ding, Y.
College/School:College of Science and Engineering > School of Computing Science

University Staff: Request a correction | Enlighten Editors: Update this record