Picture for Lan Xu

Lan Xu

ShanghaiTech University, China

CADSpotting: Robust Panoptic Symbol Spotting on Large-Scale CAD Drawings

Add code
Dec 10, 2024
Viaarxiv icon

AerialGo: Walking-through City View Generation from Aerial Perspectives

Add code
Nov 29, 2024
Figure 1 for AerialGo: Walking-through City View Generation from Aerial Perspectives
Figure 2 for AerialGo: Walking-through City View Generation from Aerial Perspectives
Figure 3 for AerialGo: Walking-through City View Generation from Aerial Perspectives
Figure 4 for AerialGo: Walking-through City View Generation from Aerial Perspectives
Viaarxiv icon

SMGDiff: Soccer Motion Generation using diffusion probabilistic models

Add code
Nov 25, 2024
Viaarxiv icon

Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos

Add code
Sep 12, 2024
Viaarxiv icon

HiSC4D: Human-centered interaction and 4D Scene Capture in Large-scale Space Using Wearable IMUs and LiDAR

Add code
Sep 09, 2024
Figure 1 for HiSC4D: Human-centered interaction and 4D Scene Capture in Large-scale Space Using Wearable IMUs and LiDAR
Figure 2 for HiSC4D: Human-centered interaction and 4D Scene Capture in Large-scale Space Using Wearable IMUs and LiDAR
Figure 3 for HiSC4D: Human-centered interaction and 4D Scene Capture in Large-scale Space Using Wearable IMUs and LiDAR
Figure 4 for HiSC4D: Human-centered interaction and 4D Scene Capture in Large-scale Space Using Wearable IMUs and LiDAR
Viaarxiv icon

SCOPE: Sign Language Contextual Processing with Embedding from LLMs

Add code
Sep 02, 2024
Viaarxiv icon

HeadGAP: Few-shot 3D Head Avatar via Generalizable Gaussian Priors

Add code
Aug 12, 2024
Figure 1 for HeadGAP: Few-shot 3D Head Avatar via Generalizable Gaussian Priors
Figure 2 for HeadGAP: Few-shot 3D Head Avatar via Generalizable Gaussian Priors
Figure 3 for HeadGAP: Few-shot 3D Head Avatar via Generalizable Gaussian Priors
Figure 4 for HeadGAP: Few-shot 3D Head Avatar via Generalizable Gaussian Priors
Viaarxiv icon

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

Add code
Jul 30, 2024
Figure 1 for StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset
Figure 2 for StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset
Figure 3 for StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset
Figure 4 for StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset
Viaarxiv icon

CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

Add code
May 30, 2024
Viaarxiv icon

Know in AdVance: Linear-Complexity Forecasting of Ad Campaign Performance with Evolving User Interest

Add code
May 17, 2024
Viaarxiv icon