Xinyu Huang

13 papers · 2022–2026 · 6 conferences · across top CS/AI conferences

Achievements

+7 more ↓

🗺️ Taxonomy Completionist (28) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (6) 🌈 Renaissance Researcher (6) 🧭 Keyword Pioneer

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (6) 🤝 Dynamic Duo (10) ⚡ Prolific Year (5) 💎 Century Club (12) 🔥 Unstoppable (5) 🗃️ Keyword Collector (68)

Conferences

CVPR (5) AAAI (2) ECCV (2) ICCV (2) ICLR (1) NIPS (1)

Top co-authors

Liu Ren (10) Yuliang Guo (10) Cheng Zhao (4) Ruoyu Wang (3) Abhinav Kumar (3) Su Sun (2) Guoquan Huang (2) Xiaoming Liu (2) Yingjie Victor Chen (2) S. Mahdi H. Miangoleh (1)

Keywords

3d object detection (2) monocular 3d detection (2) scene understanding (2) object detection (2) depth estimation (2) optimal transport (1) bird's eye view (1) domain generalization (1) monocular depth estimation (1) mixture of expert (1) uncertainty quantification (1) object localization (1) language grounding (1) outlier detection (1) spatial representation (1) autonomous driving (1) generative model (1) 3d gaussian splatting (1) data augmentation (1) semantic segmentation (1)

Papers

ExpertAD: Enhancing Autonomous Driving Systems with Mixture of Experts AAAI 2026 Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera CVPR 2025 CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector ICCV 2025 Online Language Splatting ICCV 2025 Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion CVPR 2024 SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects CVPR 2024 TCLC-GS: Tightly Coupled LiDAR-Camera Gaussian Splatting for Autonomous Driving ECCV 2024 SUP-NeRF: A Streamlined Unification of Pose Estimation and NeRF for Monocular 3D Object Reconstruction ECCV 2024 Tag2Text: Guiding Vision-Language Model via Image Tagging ICLR 2024 3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection NIPS 2023 Jointly Imputing Multi-View Data with Optimal Transport AAAI 2023 OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion CVPR 2022 Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation CVPR 2022