Picture for Baigui Sun

Baigui Sun

FaceChain-FACT: Face Adapter with Decoupled Training for Identity-preserved Personalization

Add code
Oct 16, 2024
Viaarxiv icon

TopoFR: A Closer Look at Topology Alignment on Face Recognition

Add code
Oct 14, 2024
Viaarxiv icon

ControLRM: Fast and Controllable 3D Generation via Large Reconstruction Model

Add code
Oct 12, 2024
Figure 1 for ControLRM: Fast and Controllable 3D Generation via Large Reconstruction Model
Figure 2 for ControLRM: Fast and Controllable 3D Generation via Large Reconstruction Model
Figure 3 for ControLRM: Fast and Controllable 3D Generation via Large Reconstruction Model
Figure 4 for ControLRM: Fast and Controllable 3D Generation via Large Reconstruction Model
Viaarxiv icon

Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning

Add code
Oct 08, 2024
Figure 1 for Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Figure 2 for Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Figure 3 for Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Figure 4 for Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Viaarxiv icon

Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony

Add code
Aug 18, 2024
Figure 1 for Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony
Figure 2 for Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony
Figure 3 for Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony
Figure 4 for Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony
Viaarxiv icon

Dataset Growth

Add code
May 28, 2024
Viaarxiv icon

RobustMVS: Single Domain Generalized Deep Multi-view Stereo

Add code
May 15, 2024
Figure 1 for RobustMVS: Single Domain Generalized Deep Multi-view Stereo
Figure 2 for RobustMVS: Single Domain Generalized Deep Multi-view Stereo
Figure 3 for RobustMVS: Single Domain Generalized Deep Multi-view Stereo
Figure 4 for RobustMVS: Single Domain Generalized Deep Multi-view Stereo
Viaarxiv icon

TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On

Add code
Apr 01, 2024
Figure 1 for TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On
Figure 2 for TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On
Figure 3 for TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On
Figure 4 for TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On
Viaarxiv icon

Beyond Talking -- Generating Holistic 3D Human Dyadic Motion for Communication

Add code
Mar 28, 2024
Viaarxiv icon

DyRoNet: A Low-Rank Adapter Enhanced Dynamic Routing Network for Streaming Perception

Add code
Mar 15, 2024
Viaarxiv icon