PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm

1 code implementation • 12 Oct 2023 • Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Tong He, Wanli Ouyang

In this paper, we introduce a novel universal 3D pre-training framework designed to facilitate the acquisition of efficient 3D representation, thereby establishing a pathway to 3D foundational models.

3D Object Detection 3D Reconstruction +5

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving

1 code implementation • 12 Oct 2023 • Honghui Yang, Sha Zhang, Di Huang, Xiaoyang Wu, Haoyi Zhu, Tong He, Shixiang Tang, Hengshuang Zhao, Qibo Qiu, Binbin Lin, Xiaofei He, Wanli Ouyang

In the context of autonomous driving, the significance of effective feature learning is widely acknowledged.

3D Object Detection 3D Semantic Segmentation +3

M$^3$CS: Multi-Target Masked Point Modeling with Learnable Codebook and Siamese Decoders

no code implementations • 23 Sep 2023 • Qibo Qiu, Honghui Yang, Wenxiao Wang, Shun Zhang, Haiming Gao, Haochao Ying, Wei Hua, Xiaofei He

Specifically, with masked point cloud as input, M$^3$CS introduces two decoders to predict masked representations and the original points simultaneously.

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

1 code implementation • CVPR 2023 • Honghui Yang, Wenxiao Wang, Minghao Chen, Binbin Lin, Tong He, Hua Chen, Xiaofei He, Wanli Ouyang

The key to associating the two different representations is our introduced input-dependent Query Initialization module, which could efficiently generate reference points and content queries.

Autonomous Driving Quantization

Ponder: Point Cloud Pre-training via Neural Rendering

no code implementations • ICCV 2023 • Di Huang, Sida Peng, Tong He, Honghui Yang, Xiaowei Zhou, Wanli Ouyang

We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural rendering.

3D Reconstruction Image Generation +2

GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds

1 code implementation • CVPR 2023 • Honghui Yang, Tong He, Jiaheng Liu, Hua Chen, Boxi Wu, Binbin Lin, Xiaofei He, Wanli Ouyang

In contrast to previous 3D MAE frameworks, which either design a complex decoder to infer masked information from maintained regions or adopt sophisticated masking strategies, we instead propose a much simpler paradigm.

3D-QueryIS: A Query-based Framework for 3D Instance Segmentation

no code implementations • 17 Nov 2022 • Jiaheng Liu, Tong He, Honghui Yang, Rui Su, Jiayi Tian, Junran Wu, Hongcheng Guo, Ke Xu, Wanli Ouyang

Previous top-performing methods for 3D instance segmentation often maintain inter-task dependencies and the tendency towards a lack of robustness.

3D Instance Segmentation Segmentation +1

Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph

1 code implementation • 7 Aug 2022 • Honghui Yang, Zili Liu, Xiaopei Wu, Wenxiao Wang, Wei Qian, Xiaofei He, Deng Cai

The dynamic farthest voxel sampling is then applied to evenly sample the points.

3D Object Detection object-detection

Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion

1 code implementation • CVPR 2022 • Xiaopei Wu, Liang Peng, Honghui Yang, Liang Xie, Chenxi Huang, Chengqi Deng, Haifeng Liu, Deng Cai

Many multi-modal methods are proposed to alleviate this issue, while different representations of images and point clouds make it difficult to fuse them, resulting in suboptimal performance.

3D Object Detection Data Augmentation +3

Suppress-and-Refine Framework for End-to-End 3D Object Detection

1 code implementation • 18 Mar 2021 • Zili Liu, Guodong Xu, Honghui Yang, Minghao Chen, Kuoliang Wu, Zheng Yang, Haifeng Liu, Deng Cai

In this work, we propose a suppress-and-refine framework to remove these handcrafted components.

3D Object Detection object-detection