SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.12106 · 2021

Temp-Frustum Net: 3D Object Detection with Temporal Fusion

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

3D object detection is a core component of automated driving systems. State-of-the-art methods fuse RGB imagery and LiDAR point cloud data frame-by-frame for 3D bounding box regression. However, frame-by-frame 3D object detection suffers from noise, field-of-view obstruction, and sparsity. We propose a novel Temporal Fusion Module (TFM) to use information from previous time-steps to mitigate these problems. First, a state-of-the-art frustum network extracts point cloud features from raw RGB and LiDAR point cloud data frame-by-frame. Then, our TFM module fuses these features with a recurrent neural network. As a result, 3D object detection becomes robust against single frame failures and transient occlusions. Experiments on the KITTI object tracking dataset show the efficiency of the proposed TFM, where we obtain ~6%, ~4%, and ~6% improvements on Car, Pedestrian, and Cyclist classes, respectively, compared to frame-by-frame baselines. Furthermore, ablation studies reinforce that the subject of improvement is temporal fusion and show the effects of different placements of TFM in the object detection pipeline. Our code is open-source and available at https://github.com/emecercelik/Temp-Frustum-Net.git.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.12106")
get_code_for_paper("2104.12106")
have("2104.12106")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2104.12106.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2104.12106.svg)](https://syntology.ai/paper/2104.12106)

Connect an agent — have() is free.