49 citations · 202 across the 24 of their papers we have counts for
25 papers
DriveZero: End-to-End Driving Beyond Human Demonstrations
Hao He, Chengcheng Hu, Zirun Su +17
Most end-to-end autonomous-driving systems learn by imitating human driving logs, leaving their learned behavior constrained by the quality and behavioral coverage of the recorded…
RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation
Xiaolei Lang, Ze Kang, Zehao Huang +1
Novel view synthesis from sparse inputs requires both geometric grounding from the observed views and generative priors of unobserved regions, motivating recent hybrid methods that…
Geometry-Grounded Unified 3D Perception for Autonomous Driving
Longfei Xu, Xiaohui Wang, Zehao Huang +4
Camera-based autonomous driving perception requires a shared representation that preserves metric 3D structure across synchronized multi-camera streams. However, existing image-bas…
ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?
Han Li, Si Liu, Zehao Huang +6
Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse expert-level tasks, but they still struggle with fundamental abilities that humans naturall…
Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior
Jiahui Fu, Zehao Huang, Han Li +2
Lane topology reasoning aims to construct a lane graph from onboard sensor observations. Existing methods follow a detection and association paradigm that treats each lane instance…
Geometry-Guided 3D Visual Token Pruning for Video-Language Models
Han Li, Zehao Huang, Jiahui Fu +2
Multimodal large language models have demonstrated remarkable capabilities in 2D vision, motivating their extension to 3D scene understanding. Recent studies represent 3D scenes as…
Utonia: Toward One Encoder for All Point Clouds
Yujia Zhang, Xiaoyang Wu, Yunhan Yang +6
We dream of a future where point clouds from all domains can come together to shape a single model that benefits them all. Toward this goal, we present Utonia, a first step toward…
Anchor3DLane++: 3D Lane Detection via Sample-Adaptive Sparse 3D Anchor Regression
Shaofei Huang, Zhenwei Shen, Zehao Huang +4
In this paper, we focus on the challenging task of monocular 3D lane detection. Previous methods typically adopt inverse perspective mapping (IPM) to transform the Front-Viewed (FV…
MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection
Zitian Wang, Zehao Huang, Yulu Gao +2
The rise of autonomous vehicles has significantly increased the demand for robust 3D object detection systems. While cameras and LiDAR sensors each offer unique advantages--cameras…
Enhancing 3D Lane Detection and Topology Reasoning with 2D Lane Priors
Han Li, Zehao Huang, Zitian Wang +3
3D lane detection and topology reasoning are essential tasks in autonomous driving scenarios, requiring not only detecting the accurate 3D coordinates on lane lines, but also reaso…
SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception
Yiheng Li, Hongyang Li, Zehao Huang +2
Multi-modal 3D object detection has exhibited significant progress in recent years. However, most existing methods can hardly scale to long-range scenarios due to their reliance on…
TSTTC: A Large-Scale Dataset for Time-to-Contact Estimation in Driving Scenarios
Yuheng Shi, Zehao Huang, Yan Yan +2
Time-to-Contact (TTC) estimation is a critical task for assessing collision risk and is widely used in various driver assistance and autonomous driving systems. The past few decade…
Tracking Objects with 3D Representation from Videos
Jiawei He, Lue Fan, Yuqi Wang +4
Data association is a knotty problem for 2D Multiple Object Tracking due to the object occlusion. However, in 3D space, data association is not so hard. Only with a 3D Kalman Filte…
Fully Sparse Fusion for 3D Object Detection
Yingyan Li, Lue Fan, Yang Liu +4
Currently prevalent multimodal 3D detection methods are built upon LiDAR-based detectors that usually use dense Bird's-Eye-View (BEV) feature maps. However, the cost of such BEV fe…
Learnable Graph Matching: A Practical Paradigm for Data Association
Jiawei He, Zehao Huang, Naiyan Wang +1
Data association is at the core of many computer vision tasks, e.g., multiple object tracking, image matching, and point cloud registration. however, current data association solut…
Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection
Shaofei Huang, Zhenwei Shen, Zehao Huang +5
Monocular 3D lane detection is a challenging task due to its lack of depth information. A popular solution is to first transform the front-viewed (FV) images or features into the b…
Object as Query: Lifting any 2D Object Detector to 3D Detection
Zitian Wang, Zehao Huang, Jiahui Fu +2
3D object detection from multi-view images has drawn much attention over the past few years. Existing methods mainly establish 3D representations from multi-view images and adopt a…
PredNAS: A Universal and Sample Efficient Neural Architecture Search Framework
Liuchun Yuan, Zehao Huang, Naiyan Wang
In this paper, we present a general and effective framework for Neural Architecture Search (NAS), named PredNAS. The motivation is that given a differentiable performance estimatio…
Direct Differentiable Augmentation Search
Aoming Liu, Zehao Huang, Zhiwu Huang +1
Data augmentation has been an indispensable tool to improve the performance of deep neural networks, however the augmentation can hardly transfer among different tasks and datasets…
Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking
Jiawei He, Zehao Huang, Naiyan Wang +1
Data association across frames is at the core of Multiple Object Tracking (MOT) task. This problem is usually solved by a traditional graph-based optimization or directly learned v…
QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
Chenhongyi Yang, Zehao Huang, Naiyan Wang
While general object detection with deep learning has achieved great success in the past few years, the performance and efficiency of detecting small objects are far from satisfact…
1st Place Solutions of Waymo Open Dataset Challenge 2020 -- 2D Object Detection Track
Zehao Huang, Zehui Chen, Qiaofei Li +2
In this technical report, we present our solutions of Waymo Open Dataset (WOD) Challenge 2020 - 2D Object Track. We adopt FPN as our basic framework. Cascade RCNN, stacked PAFPN Ne…
SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition
Yuntao Chen, Chenxia Han, Yanghao Li +4
Object detection and instance recognition play a central role in many AI applications like autonomous driving, video surveillance and medical image analysis. However, training obje…
You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization
Xinbang Zhang, Zehao Huang, Naiyan Wang
Recently Neural Architecture Search (NAS) has aroused great interest in both academia and industry, however it remains challenging because of its huge and non-continuous search spa…