MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships

By Yongjian Chen, Lei Tai, Kai-Lung Sun, Mingyang Li. Computer Vision and Pattern Recognition, 2020

327 citations recorded by the source corpus.

Monocular 3D object detection is an essential component in autonomous driving while challenging to solve, especially for those occluded samples which are only partially visible. Most detectors consider each 3D object as an independent training target, inevitably resulting in a lack of useful information for occluded samples. To this end, we propose a novel method to improve the monocular 3D object detection by considering the relationship of paired samples. This allows us to encode spatial constraints for partially-occluded objects from their adjacent neighbors. Specifically, the proposed detector computes uncertainty-aware predictions for object locations and 3D distances for the adjacent object pairs, which are subsequently jointly optimized by nonlinear least squares. Finally, the one-stage uncertainty-aware prediction structure and the post-optimization module are dedicatedly integrated for ensuring the run-time efficiency. Experiments demonstrate that our method yields the best performance on KITTI 3D detection benchmark, by outperforming state-of-the-art competitors by wide margins, especially for the hard samples.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/573e1ab1d368d16fd1404b639912610d900da9ad

How researchers see this paper

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

In Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

3D Object Detection for Autonomous Driving: A Comprehensive Survey (2022, background): “63 - - - MonoPair [47] Camera Monocular 2020 60 13.”
Categorical Depth Distribution Network for Monocular 3D Object Detection (2021, methodology): “Our method also outperforms the previous state-of-the art method on the Pedestrian class MonoPair [12] with margins on AP|R40 of +2.85%, +1.46%, and +1.23%.”
Probabilistic and Geometric Depth: Detecting Objects in Perspective (2021, background): “In contrast, anchor-free methods [26, 14, 42, 15] do not need to make statistics on the given data and have better generalized ability to more various classes or different intrinsic settings, so we choose to follow this paradigm.”
SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving (2023, methodology): “Other methods implicitly learn 3D features without producing explicit depth maps [53, 29, 55, 34, 52, 63].”
Geometry Uncertainty Projection Network for Monocular 3D Object Detection (2021, methodology): “A 3D offset branch aims to estimate the 3D center projection on the 2D feature maps [10].”
Delving into Localization Errors for Monocular 3D Object Detection (2021, methodology): “Specifically, the proposed method performs better than [2] and gets comparable results with [10].”
FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection (2021, background): “In contrast, anchor-free methods [37, 16, 5] do not need to make statistics on the given data.”
A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving (2020, background): “Most studies to date employ LiDARs [8]–[11], [15]–[17], [80], [89] and RGB cameras [6], [7], [13], [14], [65], [81]–[83], [87], [105] in probabilistic object detection.”
Is Pseudo-Lidar needed for Monocular 3D Object detection? (2021, background): “Incorporating uncertainty in estimating the 3D box (or its depth) has also been shown to greatly improve detection accuracy [59, 9, 58].”