Picture for Shenghua Gao

Shenghua Gao

FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction

Add code
Dec 12, 2024
Viaarxiv icon

Scaling Mesh Generation via Compressive Tokenization

Add code
Nov 11, 2024
Figure 1 for Scaling Mesh Generation via Compressive Tokenization
Figure 2 for Scaling Mesh Generation via Compressive Tokenization
Figure 3 for Scaling Mesh Generation via Compressive Tokenization
Figure 4 for Scaling Mesh Generation via Compressive Tokenization
Viaarxiv icon

CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM

Add code
Nov 07, 2024
Figure 1 for CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM
Figure 2 for CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM
Figure 3 for CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM
Figure 4 for CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM
Viaarxiv icon

Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenes

Add code
Sep 27, 2024
Figure 1 for Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenes
Figure 2 for Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenes
Figure 3 for Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenes
Figure 4 for Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenes
Viaarxiv icon

GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer

Add code
Aug 13, 2024
Figure 1 for GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer
Figure 2 for GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer
Figure 3 for GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer
Figure 4 for GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer
Viaarxiv icon

Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Video

Add code
Jul 23, 2024
Figure 1 for Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Video
Figure 2 for Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Video
Figure 3 for Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Video
Figure 4 for Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Video
Viaarxiv icon

MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis

Add code
Jul 18, 2024
Figure 1 for MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis
Figure 2 for MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis
Figure 3 for MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis
Figure 4 for MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis
Viaarxiv icon

FCA-RAC: First Cycle Annotated Repetitive Action Counting

Add code
Jun 18, 2024
Viaarxiv icon

3D StreetUnveiler with Semantic-Aware 2DGS

Add code
May 28, 2024
Figure 1 for 3D StreetUnveiler with Semantic-Aware 2DGS
Figure 2 for 3D StreetUnveiler with Semantic-Aware 2DGS
Figure 3 for 3D StreetUnveiler with Semantic-Aware 2DGS
Figure 4 for 3D StreetUnveiler with Semantic-Aware 2DGS
Viaarxiv icon

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

Add code
Apr 14, 2024
Viaarxiv icon