16 citations · 27 across the 5 of their papers we have counts for
5 papers · 1 filter
FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flow
Zhaoyang Huang, Xiaoyu Shi, Chao Zhang +6
This paper introduces a novel transformer-based network architecture, FlowFormer, along with the Masked Cost Volume AutoEncoding (MCVA) for pretraining it to tackle the problem of…
TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses
Xuesong Chen, Shaoshuai Shi, Chao Zhang +5
3D multi-object tracking (MOT) is vital for many applications including autonomous driving vehicles and service robots. With the commonly used tracking-by-detection paradigm, 3D MO…
Learning a Structured Latent Space for Unsupervised Point Cloud Completion
Yingjie Cai, Kwan-Yee Lin, Chao Zhang +3
Unsupervised point cloud completion aims at estimating the corresponding complete point cloud of a partial point cloud in an unpaired manner. It is a crucial but challenging proble…
FlowFormer: A Transformer Architecture for Optical Flow
Zhaoyang Huang, Xiaoyu Shi, Chao Zhang +5
We introduce optical Flow transFormer, dubbed as FlowFormer, a transformer-based neural network architecture for learning optical flow. FlowFormer tokenizes the 4D cost volume buil…
Semantic Scene Completion via Integrating Instances and Scene in-the-Loop
Yingjie Cai, Xuesong Chen, Chao Zhang +3
Semantic Scene Completion aims at reconstructing a complete 3D scene with precise voxel-wise semantics from a single-view depth or RGBD image. It is a crucial but challenging probl…