Picture for Shengfeng He

Shengfeng He

SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generation

Add code
Mar 25, 2025
Viaarxiv icon

NexusGS: Sparse View Synthesis with Epipolar Depth Priors in 3D Gaussian Splatting

Add code
Mar 24, 2025
Viaarxiv icon

Knowledge Bridger: Towards Training-free Missing Multi-modality Completion

Add code
Feb 27, 2025
Viaarxiv icon

RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation

Add code
Feb 18, 2025
Viaarxiv icon

Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning

Add code
Feb 04, 2025
Viaarxiv icon

Dr. Tongue: Sign-Oriented Multi-label Detection for Remote Tongue Diagnosis

Add code
Jan 06, 2025
Viaarxiv icon

MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attention

Add code
Jan 01, 2025
Figure 1 for MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attention
Figure 2 for MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attention
Figure 3 for MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attention
Figure 4 for MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attention
Viaarxiv icon

PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem Equilibrium

Add code
Dec 20, 2024
Viaarxiv icon

Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection

Add code
Dec 02, 2024
Viaarxiv icon

Morpho-Aware Global Attention for Image Matting

Add code
Nov 15, 2024
Figure 1 for Morpho-Aware Global Attention for Image Matting
Figure 2 for Morpho-Aware Global Attention for Image Matting
Figure 3 for Morpho-Aware Global Attention for Image Matting
Figure 4 for Morpho-Aware Global Attention for Image Matting
Viaarxiv icon