Photo

Yuan Liu (刘缘)

Ph.D. Student at HKU

yuanly@connect.hku.hk

I'm currently a final-year PhD student at HKU advised by Prof. Wenping Wang and Prof. Taku Komura. In 2018-2019, I worked in CAD&CG lab of Zhejiang University advised by Prof. Xiaowei Zhou. I received my master degree at LIESMARS of Wuhan University advised by Prof. Bisheng Yang. My research interest includes computer graphics and 3D computer vision. I currently work on topics about 3D AIGC including neural rendering/representations and diffusion generative models.

I'll graduate before Jul. 2024 and I'm looking for a research position on CG and 3D CV (Diffusion/NeRF/NeuS/GS)!

[Github]   [Twitter]   [Google Scholar]

Publications


*Equal contribution †Corresponding author
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
arXiv 2023
FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
arXiv 2023
Wonder3D: Single Image to 3D using Cross-Domain Diffusion
arXiv 2023
NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images
SIGGRAPH 2023
F2NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories
CVPR 2023 (Highlight)
Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
CVPR 2023
NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologies
CVPR 2023
RoReg: Pairwise Point Cloud Registration with Oriented Descriptors and Local Rotations
TPAMI 2023 *Equal contribution †Corresponding author
Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images
ECCV 2022
Neural Rays for Occlusion-aware Image-based Rendering
CVPR 2022
You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors
ACM MM 2022
NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
NeurIPS 2021 (Spotlight)
AdaFit: Rethinking Learning-based Normal Estimation on Point Clouds
ICCV 2021 (Oral)
Point2Skeleton: Learning Skeletal Representations from Point Clouds
CVPR 2021 (Oral)
Learnable Motion Coherence for Correspondence Pruning
CVPR 2021
GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs
NeurIPS 2019
PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation
CVPR 2019 (Oral)
3D Local Feature BKD to Extract Road Information from Mobile Laser Scanning Point Clouds
ISPRS Journal of Photogrammetry and Remote Sensing, 2017
A Novel Binary Shape Context for 3D Local Surface Description
ISPRS Journal of Photogrammetry and Remote Sensing, 2017
Computing Multiple Aggregation Levels and Contextual Features for Road Facilities Recognition Using Mobile Laser Scanning Data
ISPRS Journal of Photogrammetry and Remote Sensing, 2017
Automatic Registration of Large-scale Urban Scene Point Clouds Based on Semantic Feature Points
ISPRS Journal of Photogrammetry and Remote Sensing, 2016



©Yuan Liu.  Last updated: 5th Dec., 2023.