mlsanityData to 7 Oct 2026

Towards Safe, Real-Time Systems: Stereo vs Images and LiDAR for 3D Object Detection

arXiv 2202.12773 ↗First posted 25 Feb 2022cs.CV cs.LG cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

As object detectors rapidly improve, attention has expanded past image-only networks to include a range of 3D and multimodal frameworks, especially ones that incorporate LiDAR. However, due to cost, logistics, and even some safety considerations, stereo can be an appealing alternative. Towards understanding the efficacy of stereo as a replacement for monocular input or LiDAR in object detectors, we show that multimodal learning with traditional disparity algorithms can improve image-based results without increasing the number of parameters, and that learning over stereo error can impart similar 3D localization power to LiDAR in certain contexts. Furthermore, doing so also has calibration benefits with respect to image-only methods. We benchmark on the public dataset KITTI, and in doing so, reveal a few small but common algorithmic mistakes currently used in computing metrics on that set, and offer efficient, provably correct alternatives.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 17 references that are in the map. First posted on arXiv 25 Feb 2022.

Builds on

11 of 17 references.

References · 11

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  3. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  4. 2014Learning Rich Features from RGB-D Images for Object Detection and Segmentationcited by 124
  5. 2020DSGN: Deep Stereo Geometry Network for 3D Object Detectioncited by 100
  6. 2018Hierarchical Discrete Distribution Decomposition for Match Density Estimationcited by 93
  7. 20163D Object Proposals using Stereo Imagery for Accurate Object Class Detectioncited by 58
  8. 2020Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimationcited by 43
  9. 2018YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloudcited by 32
  10. 2018Tiny SSD: A Tiny Single-shot Detection Deep Convolutional Neural Network for Real-time Embedded Object Detectioncited by 8
  11. 2020LRPD: Long Range 3D Pedestrian Detection Leveraging Specific Strengths of LiDAR and RGBcited by 7

Built on by

Not cited yet.