6 papers
AeroLLE: Constrained Pseudo-Supervision for Nighttime Aerial Image Enhancement with the AeroNight-1.5K Benchmark
Wei Lu, Hongyuan Liu, Si-Bao Chen
Nighttime aerial image enhancement is challenged by spatially nonuniform exposure, mixed illumination, and weak structural evidence, while registered normal-light targets are diffi…
Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images
Hongyuan Liu, Bochao Zou, Qiankun Liu +10
Creating realistic and simulation-ready 3D assets is crucial for autonomous driving research and virtual environment construction. However, existing 3D vehicle generation methods a…
XYZCylinder: Towards Compatible Feed-Forward 3D Gaussian Splatting for Driving Scenes via Unified Cylinder Lifting Method
Haochen Yu, Qiankun Liu, Hongyuan Liu +4
Feed-forward paradigms for 3D reconstruction have become a focus of recent research, which learn implicit, fixed view transformations to generate a single scene representation. How…
MVSMamba: Multi-View Stereo with State Space Model
Jianfei Jiang, Qiankun Liu, Hongyuan Liu +4
Robust feature representations are essential for learning-based Multi-View Stereo (MVS), which relies on accurate feature matching. Recent MVS methods leverage Transformers to capt…
InstDrive: Instance-Aware 3D Gaussian Splatting for Driving Scenes
Hongyuan Liu, Haochen Yu, Bochao Zou +4
Reconstructing dynamic driving scenes from dashcam videos has attracted increasing attention due to its significance in autonomous driving and scene understanding. While recent adv…
MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network
Jianfei Jiang, Qiankun Liu, Haochen Yu +4
Learning-based Multi-View Stereo (MVS) methods aim to predict depth maps for a sequence of calibrated images to recover dense point clouds. However, existing MVS methods often stru…