6 citations · 14 across the 33 of their papers we have counts for
12 papers · 1 filter
Preventing Local Pitfalls in Vector Quantization via Optimal Transport
Borui Zhang, Wenzhao Zheng, Jie Zhou +1
Vector-quantized networks (VQNs) have exhibited remarkable performance across various tasks, yet they are prone to training instability, which complicates the training process due…
GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction
Sicheng Zuo, Wenzhao Zheng, Yuanhui Huang +2
3D occupancy prediction is important for autonomous driving due to its comprehensive perception of the surroundings. To incorporate sequential inputs, most existing methods fuse re…
Doe-1: Closed-Loop Autonomous Driving with Large World Model
Wenzhao Zheng, Zetian Xia, Yuanhui Huang +3
End-to-end autonomous driving has received increasing attention due to its potential to learn from large amounts of data. However, most existing methods are still open-loop and suf…
Owl-1: Omni World Model for Consistent Long Video Generation
Yuanhui Huang, Wenzhao Zheng, Yuan Gao +5
Video generation models (VGMs) have received extensive attention recently and serve as promising candidates for general-purpose large vision models. While they can only generate sh…
GPD-1: Generative Pre-training for Driving
Zixun Xie, Sicheng Zuo, Wenzhao Zheng +5
Modeling the evolutions of driving scenarios is important for the evaluation and decision-making of autonomous driving systems. Most existing methods focus on one aspect of scene e…
Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model
Lening Wang, Wenzhao Zheng, Dalong Du +8
4D driving simulation is essential for developing realistic autonomous driving simulators. Despite advancements in existing methods for generating driving scenes, significant chall…
EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding
Yuqi Wu, Wenzhao Zheng, Sicheng Zuo +3
3D occupancy prediction provides a comprehensive description of the surrounding scenes and has become an essential task for 3D perception. Most existing methods focus on offline pe…
Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation
Sule Bai, Yong Liu, Yifei Han +4
Recent advancements in pre-trained vision-language models like CLIP have enabled the task of open-vocabulary segmentation. CLIP demonstrates impressive zero-shot capabilities in va…
V2M: Visual 2-Dimensional Mamba for Image Representation Learning
Chengkun Wang, Wenzhao Zheng, Yuanhui Huang +2
Mamba has garnered widespread attention due to its flexible design and efficient hardware performance to process 1D sequences based on the state space model (SSM). Recent studies h…
GlobalMamba: Global Image Serialization for Vision Mamba
Chengkun Wang, Wenzhao Zheng, Jie Zhou +1
Vision mambas have demonstrated strong performance with linear complexity to the number of vision tokens. Their efficiency results from processing image tokens sequentially. Howeve…
GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction
Yuanhui Huang, Wenzhao Zheng, Yunpeng Zhang +2
3D semantic occupancy prediction aims to obtain 3D fine-grained geometry and semantics of the surrounding scene and is an important task for the robustness of vision-centric autono…
Path Choice Matters for Clear Attribution in Path Methods
Borui Zhang, Wenzhao Zheng, Jie Zhou +1
Rigorousness and clarity are both essential for interpretations of DNNs to engender human trust. Path methods are commonly employed to generate rigorous attributions that satisfy t…