Lan Xu

44 papers · 2020–2025 · 6 conferences · across top CS/AI conferences

Achievements

🗺️ Taxonomy Completionist (69) 🏃 Academic Marathon (5) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (14) 🌈 Renaissance Researcher (9) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (6) 🏠 Conference Loyalist (28) 🏆 Keyword Champion (4) 🤝 Dynamic Duo (30) 🔬 Deep Specialist (26) 🗃️ Keyword Collector (212) ⚡ Prolific Year (6) 💎 Century Club (44) 🔥 Unstoppable (6)

Conferences

CVPR (28) AAAI (7) ICCV (4) IJCAI (3) ECCV (1) NIPS (1)

Top co-authors

Jingyi Yu (30) Yuexin Ma (14) Jingya Wang (14) Minye Wu (10) Ye Shi (7) Siqi Shen (6) Cheng Wang (6) Juze Zhang (6) Zhuo Su (6) Chenglu Wen (6)

Research topics

Computer Vision (1)

Keywords

3d reconstruction (15) human pose estimation (10) novel view synthesis (8) pose estimation (8) neural radiance field (8) neural rendering (7) motion capture (6) human-object interaction (6) diffusion model (5) multi-modal learning (5) human motion (4) 3d human pose estimation (4) 3d vision (4) multimodal learning (4) human motion capture (4) lidar point cloud (4) motion tracking (3) sensor fusion (3) scene understanding (3) point cloud (3)

Papers

SCOPE: Sign Language Contextual Processing with Embedding from LLMs AAAI 2025

Capturing the Unseen: Vision-Free Facial Motion Capture Using Inertial Measurement Units AAAI 2025

SMGDiff: Soccer Motion Generation using Diffusion Probabilistic Models ICCV 2025

RePerformer: Immersive Human-centric Volumetric Videos from Playback to Photoreal Reperformance CVPR 2025

ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate CVPR 2025

Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis ICCV 2025

BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics CVPR 2024

VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams CVPR 2024

I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions CVPR 2024

RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method CVPR 2024

OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers CVPR 2024

A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals CVPR 2024

HybridGait: A Benchmark for Spatial-Temporal Cloth-Changing Gait Recognition with Hybrid Explorations AAAI 2024

HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting CVPR 2024

HOI-M^3: Capture Multiple Humans and Objects Interaction within Contextual Environment CVPR 2024

LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment CVPR 2024

StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset IJCAI 2023

Weakly Supervised 3D Multi-Person Pose Estimation for Large-Scale Scenes Based on Monocular Camera and Single LiDAR AAAI 2023

HybridCap: Inertia-Aid Monocular Capture of Challenging Human Motions AAAI 2023

IKOL: Inverse Kinematics Optimization Layer for 3D Human Pose and Shape Estimation via Gauss-Newton Differentiation AAAI 2023

Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos CVPR 2023

NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions CVPR 2023

Instant-NVR: Instant Neural Volumetric Rendering for Human-Object Interactions From Monocular RGBD Stream CVPR 2023

HumanGen: Generating Human Radiance Fields With Explicit Priors CVPR 2023

Relightable Neural Human Assets From Multi-View Gradient Illuminations CVPR 2023

SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments CVPR 2023

CIMI4D: A Large Multimodal Climbing Motion Dataset Under Human-Scene Interactions CVPR 2023

Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator NIPS 2023

HumanNeRF: Efficiently Generated Human Radiance Field From Sparse Inputs CVPR 2022

HSC4D: Human-Centered 4D Scene Capture in Large-Scale Indoor-Outdoor Space Using Wearable IMUs and LiDAR CVPR 2022

NeuralHOFusion: Neural Volumetric Rendering Under Human-Object Interactions CVPR 2022

LiDARCap: Long-Range Marker-Less 3D Human Motion Capture With LiDAR Point Clouds CVPR 2022

STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes CVPR 2022

Anisotropic Fourier Features for Neural Image-Based Rendering and Relighting AAAI 2022

Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-Time CVPR 2022

PIANO: A Parametric Hand Bone Model from Magnetic Resonance Imaging IJCAI 2021

NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering Using RGB Cameras CVPR 2021

ChallenCap: Monocular 3D Capture of Challenging Human Performances Using Multi-Modal References CVPR 2021

Neural Video Portrait Relighting in Real-Time via Consistency Modeling ICCV 2021

GNeRF: GAN-Based Neural Radiance Field Without Posed Camera ICCV 2021

Few-shot Neural Human Performance Rendering from Sparse RGBD Videos IJCAI 2021

OccuSeg: Occupancy-Aware 3D Instance Segmentation CVPR 2020

RobustFusion: Human Volumetric Capture with Data-driven Visual Cues using a RGBD Camera ECCV 2020

EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event Camera CVPR 2020