167 citations · 796 across the 44 of their papers we have counts for
4 papers · 2 filters
UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation
Haiyang Wang, Hao Tang, Shaoshuai Shi +4
Jointly processing information from multiple sensors is crucial to achieving accurate and robust perception for reliable autonomous driving systems. However, current 3D perception…
ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-real Novel View Synthesis via Contrastive Learning
Hao Yang, Lanqing Hong, Aoxue Li +4
Although many recent works have investigated generalizable NeRF-based novel view synthesis for unseen scenes, they seldom consider the synthetic-to-real generalization, which is de…
Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling
Keyu Tian, Yi Jiang, Qishuai Diao +3
We identify and overcome two key obstacles in extending the success of BERT-style pre-training, or the masked image modeling, to convolutional networks (convnets): (i) convolution…
DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets
Haiyang Wang, Chen Shi, Shaoshuai Shi +5
Designing an efficient yet deployment-friendly 3D backbone to handle sparse point clouds is a fundamental problem in 3D perception. Compared with the customized sparse convolution,…