Document Type

Article

Publication Title

arXiv

Abstract

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 1st on car, pedestrian, and cyclist among the monocular 3D detectors with publications on the KITTI-3D benchmark. The code is released at https://github.com/revisitq/Pseudo-Stereo-3D. © 2022, CC BY-NC-SA.

DOI

doi.org/10.48550/arXiv.2203.02112

Publication Date

3-4-2022

Keywords

Object detection, Object recognition, Stereo image processing, 3-D detectors, 3D object, Depth Estimation, Detection framework, Feature level, Objects detection, Pseudo stereos, Single images, View generation, Virtual view, Optical radar, Computer Vision and Pattern Recognition (cs.CV)

Comments

Preprint: arXiv

Archived with thanks to arXiv

Preprint License: CC by NC-SA 4.0

Uploaded 30 May 2022

Download

Share

COinS