Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection
This paper presents a novel 3D object detection framework that processes LiDAR data directly on its native representation: range images. Benefiting from the compactness of range images, 2D convolutions can efficiently process dense LiDAR data of a scene. To overcome scale sensitivity in this perspective view, a novel range-conditioned dilation (RCD) layer is proposed to dynamically adjust a continuous dilation rate as a function of the measured range. Furthermore, localized soft range gating combined with a 3D box-refinement stage improves robustness in occluded areas, and produces overall more accurate bounding box predictions. On the public large-scale Waymo Open Dataset, our method sets a new baseline for range-based 3D detection, outperforming multiview and voxel-based methods over all ranges with unparalleled performance at long range detection.
Code (1)
Tasks
3D Object DetectionAutonomous Drivingobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Conditioned Time-Dilated Convolutions for Sound Event Detection
Sound event detection (SED) is the task of identifying sound events along with their onset and offset times. A recent, convolutional neural networks based SED method, proposed the usage of depthwise separable (DWS) and t…
Event DetectionLanguage ModellingSound Event DetectionInvariant multiscale neural networks for data-scarce scientific applications
Success of machine learning (ML) in the modern world is largely determined by abundance of data. However at many industrial and scientific problems, amount of data is limited. Application of ML methods to data-scarce sci…
Efficient Smoothing of Dilated Convolutions for Image Segmentation
Dilated Convolutions have been shown to be highly useful for the task of image segmentation. By introducing gaps into convolutional filters, they enable the use of larger receptive fields without increasing the original …
Image SegmentationSegmentationSemantic SegmentationAppearance-Based Gaze Estimation Using Dilated-Convolutions
Appearance-based gaze estimation has attracted more and more attention because of its wide range of applications. The use of deep convolutional neural networks has improved the accuracy significantly. In order to improve…
Contact DetectionGaze EstimationMulti-Scale Context Aggregation by Dilated Convolutions
State-of-the-art models for semantic segmentation are based on adaptations of convolutional networks that had originally been designed for image classification. However, dense prediction and image classification are stru…
General Classificationimage-classificationPredictionReal-Time Semantic Segmentation+2