SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.07530 · 2023

Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance

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

Weakly supervised 3D object detection aims to learn a 3D detector with lower annotation cost, e.g., 2D labels. Unlike prior work which still relies on few accurate 3D annotations, we propose a framework to study how to leverage constraints between 2D and 3D domains without requiring any 3D labels. Specifically, we employ visual data from three perspectives to establish connections between 2D and 3D domains. First, we design a feature-level constraint to align LiDAR and image features based on object-aware regions. Second, the output-level constraint is developed to enforce the overlap between 2D and projected 3D box estimations. Finally, the training-level constraint is utilized by producing accurate and consistent 3D pseudo-labels that align with the visual data. We conduct extensive experiments on the KITTI dataset to validate the effectiveness of the proposed three constraints. Without using any 3D labels, our method achieves favorable performance against state-of-the-art approaches and is competitive with the method that uses 500-frame 3D annotations. Code will be made publicly available at https://github.com/kuanchihhuang/VG-W3D.

For agents

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

get_harvested_code_for_paper("2312.07530")
get_code_for_paper("2312.07530")
have("2312.07530")

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

curl https://syntology.ai/api/ran/2312.07530.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.07530.svg)](https://syntology.ai/paper/2312.07530)

Connect an agent — have() is free.