computer-vision

Weakly Supervised 3D Detection

3260 papers • 126 benchmarks • 313 datasets

3D detection without using LiDAR annotations

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in weakly-supervised-3d-detection

Trend

Dataset

Best Model

Actions

KITTI-360

Libraries

i

Use these libraries to find weakly-supervised-3d-detection models and implementations

Datasets

KITTI-360

Subtasks

No subtasks available.

Most implemented papers

Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors

Adrien Gaidon, Sergey Zakharov, Wadim Kehl, Arjun Bhargava•Mon Nov 25 2019

An automatic annotation pipeline to recover 9D cuboids and 3D shapes from pre-trained off-the-shelf 2D detectors and sparse LIDAR data is presented and a curriculum learning strategy is proposed, iteratively retraining on samples of increasing difficulty in subsequent self-improving annotation rounds.

126

Content

0

Paper Graph

WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection

Xiaofei He, Liang Peng, Senbo Yan, Boxi Wu, Zheng Yang, Deng Cai•Tue Mar 15 2022

The weakly supervised monocular 3D detection method is explored, which first detects 2D boxes on the image and adopts corresponding RoI LiDAR points as the weak supervision, then adopts a network to predict 3D boxes which can tightly align with associated RoILiDar points.

25 0

Paper Graph

VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection

Zihua Liu, Hiroki Sakuma, Masatoshi Okutomi•Thu Mar 28 2024

A novel weakly supervised 3D object detection framework named VSRD (Volumetric Silhouette Rendering for Detection) is proposed to train 3D object detectors without any 3D supervision but only weak 2D supervision, demonstrating that this method outperforms the existing weakly supervised 3D object detection methods.

5 0

Paper Graph

Adding a benchmark result helps the community track progress.