Boosting 3D Object Detection via Object-Focused Image Fusion

Hao Yang, Chen Shi, Yihong Chen, Liwei Wang
7/21/2022
cs.CV

Official code: haoy945/DeMF (59 stars, MIT, last commit 2022-09-11).

Abstract

3D object detection has achieved remarkable progress by taking point clouds as the only input. However, point clouds often suffer from incomplete geometric structures and the lack of semantic information, which makes detectors hard to accurately classify detected objects. In this work, we focus on how to effectively utilize object-level information from images to boost the performance of point-based 3D detector. We present DeMF, a simple yet effective method to fuse image information into point features. Given a set of point features and image feature maps, DeMF adaptively aggregates image features by taking the projected 2D location of the 3D point as reference. We evaluate our method on the challenging SUN RGB-D dataset, improving state-of-the-art results by a large margin (+2.1 [email protected] and [email protected]). Code is available at https://github.com/haoy945/DeMF.

View on arXivView PDF

Code Implementations(1)

haoy945/DeMFOfficial100%
MIT

Boosting 3D Object Detection via Object-Focused Image Fusion

598Shell, PythonJul 9, 20224 years agoMIT

Similar Papers

PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection

87% match2024

GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection

87% match2025

CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer

86% match2 repos1342024

Object Detection in 3D Point Clouds via Local Correlation-Aware Point Embedding

86% match2023

PG-RCNN: Semantic Surface Point Generation for 3D Object Detection

86% match1 repo372026

PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer

85% match1 repo502026

Cite this paper

@article{yang2022boosting,
  title  = {Boosting 3D Object Detection via Object-Focused Image Fusion},
  author = {Hao Yang and Chen Shi and Yihong Chen and Liwei Wang},
  year   = {2022},
  eprint = {2207.10589},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.10589v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.10589.svg)](https://codeofpaper.com/paper/2207.10589)

Discussion