Lan Xu
YOU?
Author Swipe
View article: Sci-Tech finance, digital economy and high-quality development of regional economy: empirical evidence from 273 cities in China
Sci-Tech finance, digital economy and high-quality development of regional economy: empirical evidence from 273 cities in China Open
This study uses panel data from 273 prefecture-level cities in China between 2011 and 2022 to demonstrate that science and technology (Sci-Tech) finance significantly contributes to high-quality development in regional economies. This conc…
View article: Facial Appearance Capture at Home with Patch-Level Reflectance Prior
Facial Appearance Capture at Home with Patch-Level Reflectance Prior Open
Existing facial appearance capture methods can reconstruct plausible facial reflectance from smartphone-recorded videos. However, the reconstruction quality is still far behind the ones based on studio recordings. This paper fills the gap …
View article: BANG: Dividing 3D Assets via Generative Exploded Dynamics
BANG: Dividing 3D Assets via Generative Exploded Dynamics Open
3D creation has always been a unique human strength, driven by our ability to deconstruct and reassemble objects using our eyes, mind and hand. However, current 3D design tools struggle to replicate this natural process, requiring consider…
View article: CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image
CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image Open
Recovering high-quality 3D scenes from a single RGB image is a challenging task in computer graphics. Current methods often struggle with domain-specific limitations or low-quality object generation. To address these, we propose CAST (Comp…
View article: Facial Appearance Capture at Home with Patch-Level Reflectance Prior
Facial Appearance Capture at Home with Patch-Level Reflectance Prior Open
Existing facial appearance capture methods can reconstruct plausible facial reflectance from smartphone-recorded videos. However, the reconstruction quality is still far behind the ones based on studio recordings. This paper fills the gap …
View article: Improving Open-Set Semantic Segmentation in 3D Point Clouds by Conditional Channel Capacity Maximization: Preliminary Results
Improving Open-Set Semantic Segmentation in 3D Point Clouds by Conditional Channel Capacity Maximization: Preliminary Results Open
Point-cloud semantic segmentation underpins a wide range of critical applications. Although recent deep architectures and large-scale datasets have driven impressive closed-set performance, these models struggle to recognize or properly se…
View article: Capturing the Unseen: Vision-Free Facial Motion Capture Using Inertial Measurement Units
Capturing the Unseen: Vision-Free Facial Motion Capture Using Inertial Measurement Units Open
We present Capturing the Unseen (CAPUS), a novel facial motion capture (MoCap) technique that operates without visual signals. CAPUS leverages miniaturized Inertial Measurement Units (IMUs) as a new sensing modality for facial motion captu…
View article: CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image
CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image Open
Recovering high-quality 3D scenes from a single RGB image is a challenging task in computer graphics. Current methods often struggle with domain-specific limitations or low-quality object generation. To address these, we propose CAST (Comp…
View article: EEG-based real-time BCI system using drones for attention visualization
EEG-based real-time BCI system using drones for attention visualization Open
Attention management is crucial for cognitive development, especially in children. This study presents a novel brain-computer interface (BCI) system that uses EEG signals to classify attention states. It analyzes these signals using a wave…
View article: BEAM: Bridging Physically-based Rendering and Gaussian Modeling for Relightable Volumetric Video
BEAM: Bridging Physically-based Rendering and Gaussian Modeling for Relightable Volumetric Video Open
Volumetric video enables immersive experiences by capturing dynamic 3D scenes, enabling diverse applications for virtual reality, education, and telepresence. However, traditional methods struggle with fixed lighting conditions, while neur…
View article: TANGLED: Generating 3D Hair Strands from Images with Arbitrary Styles and Viewpoints
TANGLED: Generating 3D Hair Strands from Images with Arbitrary Styles and Viewpoints Open
Hairstyles are intricate and culturally significant with various geometries, textures, and structures. Existing text or image-guided generation methods fail to handle the richness and complexity of diverse styles. We present TANGLED, a nov…
View article: CADSpotting: Robust Panoptic Symbol Spotting on Large-Scale CAD Drawings
CADSpotting: Robust Panoptic Symbol Spotting on Large-Scale CAD Drawings Open
We introduce CADSpotting, an effective method for panoptic symbol spotting in large-scale architectural CAD drawings. Existing approaches often struggle with symbol diversity, scale variations, and overlapping elements in CAD designs, and …
View article: Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos
Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos Open
Volumetric video represents a transformative advancement in visual media, enabling users to freely navigate immersive virtual experiences and narrowing the gap between digital and real worlds. However, the need for extensive manual interve…
View article: LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives
LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives Open
Large garages are ubiquitous yet intricate scenes that present unique challenges due to their monotonous colors, repetitive patterns, reflective surfaces, and transparent vehicle glass. Conventional Structure from Motion (SfM) methods for …
View article: V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians
V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians Open
Experiencing high-fidelity volumetric video as seamlessly as 2D videos is a long-held dream. However, current dynamic 3DGS methods, despite their high rendering quality, face challenges in streaming on mobile devices due to computational a…
View article: Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos
Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos Open
Volumetric video represents a transformative advancement in visual media, enabling users to freely navigate immersive virtual experiences and narrowing the gap between digital and real worlds. However, the need for extensive manual interve…
View article: HiSC4D: Human-Centered Interaction and 4D Scene Capture in Large-Scale Space Using Wearable IMUs and LiDAR
HiSC4D: Human-Centered Interaction and 4D Scene Capture in Large-Scale Space Using Wearable IMUs and LiDAR Open
We introduce HiSC4D, a novel Human-centered interaction and 4D Scene Capture method, aimed at accurately and efficiently creating a dynamic digital world, containing large-scale indoor-outdoor scenes, diverse human motions, rich human-huma…
View article: DressCode: Autoregressively Sewing and Generating Garments from Text Guidance
DressCode: Autoregressively Sewing and Generating Garments from Text Guidance Open
Apparel's significant role in human appearance underscores the importance of garment digitalization for digital human creation. Recent advances in 3D content creation are pivotal for digital human creation. Nonetheless, garment generation …
View article: Implicit Swept Volume SDF: Enabling Continuous Collision-Free Trajectory Generation for Arbitrary Shapes
Implicit Swept Volume SDF: Enabling Continuous Collision-Free Trajectory Generation for Arbitrary Shapes Open
In the field of trajectory generation for objects, ensuring continuous collision-free motion remains a huge challenge, especially for non-convex geometries and complex environments. Previous methods either oversimplify object shapes, which…
View article: Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance
Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance Open
The synthesis of 3D facial animations from speech has garnered considerable attention. Due to the scarcity of high-quality 4D facial data and well-annotated abundant multi-modality labels, previous methods often suffer from limited realism…
View article: A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals
A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals Open
Estimating full-body human motion via sparse tracking signals from head-mounted displays and hand controllers in 3D scenes is crucial to applications in AR/VR. One of the biggest challenges to this task is the one-to-many mapping from spar…
View article: RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method
RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method Open
Comprehensive capturing of human motions requires both accurate captures of complex poses and precise localization of the human within scenes. Most of the HPE datasets and methods primarily rely on RGB, LiDAR, or IMU data. However, solely …
View article: HybridGait: A Benchmark for Spatial-Temporal Cloth-Changing Gait Recognition with Hybrid Explorations
HybridGait: A Benchmark for Spatial-Temporal Cloth-Changing Gait Recognition with Hybrid Explorations Open
Existing gait recognition benchmarks mostly include minor clothing variations in the laboratory environments, but lack persistent changes in appearance over time and space. In this paper, we propose the first in-the-wild benchmark CCGait f…
View article: Gaze-guided Hand-Object Interaction Synthesis: Dataset and Method
Gaze-guided Hand-Object Interaction Synthesis: Dataset and Method Open
Gaze plays a crucial role in revealing human attention and intention, particularly in hand-object interaction scenarios, where it guides and synchronizes complex tasks that require precise coordination between the brain, hand, and object. …
View article: LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment
LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment Open
For human-centric large-scale scenes, fine-grained modeling for 3D human global pose and shape is significant for scene understanding and can benefit many real-world applications. In this paper, we present LiveHPS, a novel single-LiDAR-bas…
View article: Capturing the Unseen: Vision-Free Facial Motion Capture Using Inertial Measurement Units
Capturing the Unseen: Vision-Free Facial Motion Capture Using Inertial Measurement Units Open
We present Capturing the Unseen (CAPUS), a novel facial motion capture (MoCap) technique that operates without visual signals. CAPUS leverages miniaturized Inertial Measurement Units (IMUs) as a new sensing modality for facial motion captu…
View article: Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance
Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance Open
The synthesis of 3D facial animations from speech has garnered considerable attention. Due to the scarcity of high-quality 4D facial data and well-annotated abundant multi-modality labels, previous methods often suffer from limited realism…
View article: OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers
OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers Open
We have recently seen tremendous progress in realistic text-to-motion generation. Yet, the existing methods often fail or produce implausible motions with unseen text inputs, which limits the applications. In this paper, we present OMG, a …
View article: BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics
BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics Open
The recently emerging text-to-motion advances have spired numerous attempts for convenient and interactive human motion generation. Yet, existing methods are largely limited to generating body motions only without considering the rich two-…