2 citations · 5 across the 26 of their papers we have counts for
29 papers
Motion- and Gravity-Aware Feedforward 3D Reconstruction
Shiyao Qian, Yuan Ren, Dongfeng Bai
Feed-forward transformer models have recently achieved strong performance in multi-view 3D reconstruction, but they still rely primarily on appearance-based attention and often str…
GeoWM: Efficient Direct World Modeling in Explicit Geometry
Mehrdad Noori, Guile Wu, Sam Hosseini +1
Modeling 3D scene geometry and its evolution over time is essential for autonomous driving and robotics. A common paradigm is to use world models to predict future images or latent…
GeoComposer: Geometry-Grounded Photographic Composition Instruction
Shuangzhi Li, Qiaoqiao Jia, Xingxin Chen +2
Photographic composition aims to provide visual guidance for improving the framing, viewpoint, and spatial arrangement of an image. Early methods primarily rely on image cropping t…
VGGT-Prime: Compute-Adaptive Mixture-of-Heads for Efficient Visual Geometry Transformers
Abteen Arab, Guile Wu, Chengjie Huang +1
Feed-forward visual geometry models such as the Visual Geometry Grounded Transformer (VGGT) have recently enabled direct 3D reconstruction from multi-view images. Despite their pro…
Chain of Spatial Thoughts: Modality-Agnostic Spatial Grounding for Vision Language Models
Hunter Schofield, Mohammed Elmahgiubi, Mohammad Mahdavian +4
Spatial understanding is fundamental to embodied intelligence, underpinning applications such as robotic manipulation, embodied navigation, and autonomous driving. Although recent…
RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning
Ehsan Ahmadi, Hunter Schofield, Behzad Khamidehi +5
Supervised open-loop training has been widely adopted for training traffic simulation models; however, it fails to capture the inherently dynamic, multi-agent interactions common i…
TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention
David Huang, Guile Wu, Chengjie Huang +2
Recent feed-forward 3D reconstruction methods, such as visual geometry transformers, have substantially advanced the traditional per-scene optimization paradigm by enabling effecti…
Part-Level 3D Gaussian Vehicle Generation with Joint and Hinge Axis Estimation
Shiyao Qian, Yuan Ren, Dongfeng Bai +1
Simulation is essential for autonomous driving, yet current frameworks often model vehicles as rigid assets and fail to capture part-level articulation. With perception algorithms…
UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception
Mohammad Mahdavian, Gordon Tan, Binbin Xu +3
We present UniScale, a unified, scale-aware multi-view 3D reconstruction framework for robotic applications that flexibly integrates geometric priors through a modular, semanticall…
Language and Geometry Grounded Sparse Voxel Representations for Holistic Scene Understanding
Guile Wu, David Huang, Bingbing Liu +1
Existing 3D open-vocabulary scene understanding methods mostly emphasize distilling language features from 2D foundation models into 3D feature fields, but largely overlook the syn…
Nighttime Autonomous Driving Scene Reconstruction with Physically-Based Gaussian Splatting
Tae-Kyeong Kim, Xingxin Chen, Guile Wu +3
This paper focuses on scene reconstruction under nighttime conditions in autonomous driving simulation. Recent methods based on Neural Radiance Fields (NeRFs) and 3D Gaussian Splat…
FreeFix: Boosting 3D Gaussian Splatting via Fine-Tuning-Free Diffusion Models
Hongyu Zhou, Zisen Shao, Sheng Miao +4
Neural Radiance Fields and 3D Gaussian Splatting have advanced novel view synthesis, yet still rely on dense inputs and often degrade at extrapolated views. Recent approaches lever…
EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesis
Sheng Miao, Sijin Li, Pan Wang +5
Novel view synthesis (NVS) of static and dynamic urban scenes is essential for autonomous driving simulation, yet existing methods often struggle to balance reconstruction time wit…
Spatial4D-Bench: A Versatile 4D Spatial Intelligence Benchmark
Pan Wang, Yang Liu, Guile Wu +23
4D spatial intelligence involves perceiving and processing how objects move or change over time. Humans naturally possess 4D spatial intelligence, supporting a broad spectrum of sp…
Monocular Visual 8D Pose Estimation for Articulated Bicycles and Cyclists
Eduardo R. Corral-Soto, Yang Liu, Yuan Ren +2
In Autonomous Driving, cyclists belong to the safety-critical class of Vulnerable Road Users (VRU), and accurate estimation of their pose is critical for cyclist crossing intention…
MoVieDrive: Urban Scene Synthesis with Multi-Modal Multi-View Video Diffusion Transformer
Guile Wu, David Huang, Dongfeng Bai +1
Urban scene synthesis with video generation models has recently shown great potential for autonomous driving. Existing video generation approaches to autonomous driving primarily f…
ArmGS: Composite Gaussian Appearance Refinement for Modeling Dynamic Urban Environments
Guile Wu, Dongfeng Bai, Bingbing Liu
This work focuses on modeling dynamic urban environments for autonomous driving simulation. Contemporary data-driven methods using neural radiance fields have achieved photorealist…
EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis
Sheng Miao, Jiaxin Huang, Dongfeng Bai +6
Novel view synthesis of urban scenes is essential for autonomous driving-related applications.Existing NeRF and 3DGS-based methods show promising results in achieving photorealisti…
CAPS: Context-Aware Priority Sampling for Enhanced Imitation Learning in Autonomous Driving
Hamidreza Mirkhani, Behzad Khamidehi, Ehsan Ahmadi +6
In this paper, we introduce Context-Aware Priority Sampling (CAPS), a novel method designed to enhance data efficiency in learning-based autonomous driving systems. CAPS addresses…
An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-assisted Training
Haiming Zhang, Ying Xue, Xu Yan +6
The field of autonomous driving is experiencing a surge of interest in world models, which aim to predict potential future scenarios based on historical observations. In this paper…
HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving
Hongyu Zhou, Longzhong Lin, Jiabao Wang +6
In the past few decades, autonomous driving algorithms have made significant progress in perception, planning, and control. However, evaluating individual components does not fully…
VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving
Haiming Zhang, Wending Zhou, Yiyao Zhu +7
This paper introduces VisionPAD, a novel self-supervised pre-training paradigm designed for vision-centric algorithms in autonomous driving. In contrast to previous approaches that…
3DArticCyclists: Generating Synthetic Articulated 8D Pose-Controllable Cyclist Data for Computer Vision Applications
Eduardo R. Corral-Soto, Yang Liu, Tongtong Cao +2
In Autonomous Driving (AD) Perception, cyclists are considered safety-critical scene objects. Commonly used publicly-available AD datasets typically contain large amounts of car an…
AutoSplat: Constrained Gaussian Splatting for Autonomous Driving Scene Reconstruction
Mustafa Khan, Hamidreza Fazlali, Dhruv Sharma +4
Realistic scene reconstruction and view synthesis are essential for advancing autonomous driving systems by simulating safety-critical scenarios. 3D Gaussian Splatting excels in re…