Hongyuan Liu

4 papers · 2025–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 👥 Mega-Team · Squad

Venues

CVPR (2) AAAI (1) ICCV (1)

Top co-authors

Haochen Yu (3) Huimin Ma (3) Jiansheng Chen (3) Bochao Zou (2) Qi Mei (2) Qiankun Liu (2) Jianfei Jiang (2) Jie Zhou (1) Ganqu Cui (1) Juntao Lyu (1)

Research topics

Computer Vision (3) Deep Learning (2) Analysis (2) Domain-Specific (2) Artificial Intelligence (1) Architectures (1) Core AI (1) Generation (1) Learning Types (1)

Keywords

autonomous driving (2) 3d reconstruction (2) self-supervised learning (1) attention mechanism (1) feature matching (1) point cloud (1) depth estimation (1) model architecture (1) gaussian splatting (1) training efficiency (1) 3d gaussian splatting (1) differentiable rendering (1) neural radiance field (1) multimodal large language model (1) multi-view stereo (1) camera pose estimation (1) text recognition (1) single-view reconstruction (1) vehicle reconstruction (1) explicit geometry (1)

Papers

MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe CVPR 2026 Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images CVPR 2026 MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network ICCV 2025 ProtoCar: Learning 3D Vehicle Prototypes from Single-View and Unconstrained Driving Scene Images AAAI 2025