Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection

03/05/2019
by   Zhixin Wang, et al.
0

In this work, we propose a novel method termed Frustum ConvNet (F-ConvNet) for amodal 3D object detection from point clouds. Given 2D region proposals in a RGB image, our method first generates a sequence of frustums for each region proposal, and uses the obtained frustums to group local points. F-ConvNet aggregates point-wise features as frustumlevel feature vectors, and arrays these feature vectors as a feature map for use of its subsequent component of fully convolutional network (FCN), which spatially fuses frustumlevel features and supports an end-to-end and continuous estimation of oriented boxes in the 3D space. We also propose component variants of L-ConvNet, including a FCN variant that extracts multi-resolution frustum features, and a refined use of L-ConvNet over a reduced 3D space. Careful ablation studies verify the efficacy of these component variants. LConvNet assumes no prior knowledge of the working 3D environment, and is thus dataset-agnostic. We present experiments on both the indoor SUN-RGBD and outdoor KITTI datasets. LConvNet outperforms all existing methods on SUN-RGBD, and at the time of submission it outperforms all published works on the KITTI benchmark. We will make the code of L-ConvNet publicly available.

READ FULL TEXT

page 1

page 7

research
12/10/2020

R-AGNO-RPN: A LIDAR-Camera Region Deep Network for Resolution-Agnostic Detection

Current neural networks-based object detection approaches processing LiD...
research
08/07/2019

Edge-guided Non-local Fully Convolutional Network for Salient Object Detection

Fully Convolutional Neural Network (FCN) has been widely applied to sali...
research
12/21/2020

3D Object Detection with Pointformer

Feature learning for 3D object detection from point clouds is very chall...
research
09/16/2015

DenseBox: Unifying Landmark Localization with End to End Object Detection

How can a single fully convolutional neural network (FCN) perform on obj...
research
08/09/2017

CoupleNet: Coupling Global Structure with Local Parts for Object Detection

The region-based Convolutional Neural Network (CNN) detectors such as Fa...
research
06/22/2020

Generative Sparse Detection Networks for 3D Single-shot Object Detection

3D object detection has been widely studied due to its potential applica...
research
04/14/2018

Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy

Fully convolutional neural network (FCN) has been dominating the game of...

Please sign up or login with your details

Forgot password? Click here to reset