photo


LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis

Add code
Dec 19, 2024
Viaarxiv icon

Personalized Generative Low-light Image Denoising and Enhancement

Add code
Dec 18, 2024
Viaarxiv icon

IDEA-Bench: How Far are Generative Models from Professional Designing?

Add code
Dec 16, 2024
Figure 1 for IDEA-Bench: How Far are Generative Models from Professional Designing?
Figure 2 for IDEA-Bench: How Far are Generative Models from Professional Designing?
Figure 3 for IDEA-Bench: How Far are Generative Models from Professional Designing?
Figure 4 for IDEA-Bench: How Far are Generative Models from Professional Designing?
Viaarxiv icon

IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation

Add code
Dec 16, 2024
Figure 1 for IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
Figure 2 for IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
Figure 3 for IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
Figure 4 for IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
Viaarxiv icon

Medical Manifestation-Aware De-Identification

Add code
Dec 14, 2024
Viaarxiv icon

What constitutes a Deep Fake? The blurry line between legitimate processing and manipulation under the EU AI Act

Add code
Dec 13, 2024
Figure 1 for What constitutes a Deep Fake? The blurry line between legitimate processing and manipulation under the EU AI Act
Figure 2 for What constitutes a Deep Fake? The blurry line between legitimate processing and manipulation under the EU AI Act
Figure 3 for What constitutes a Deep Fake? The blurry line between legitimate processing and manipulation under the EU AI Act
Figure 4 for What constitutes a Deep Fake? The blurry line between legitimate processing and manipulation under the EU AI Act
Viaarxiv icon

Human vs. AI: A Novel Benchmark and a Comparative Study on the Detection of Generated Images and the Impact of Prompts

Add code
Dec 12, 2024
Viaarxiv icon

TryOffAnyone: Tiled Cloth Generation from a Dressed Person

Add code
Dec 11, 2024
Figure 1 for TryOffAnyone: Tiled Cloth Generation from a Dressed Person
Figure 2 for TryOffAnyone: Tiled Cloth Generation from a Dressed Person
Figure 3 for TryOffAnyone: Tiled Cloth Generation from a Dressed Person
Figure 4 for TryOffAnyone: Tiled Cloth Generation from a Dressed Person
Viaarxiv icon

SenCLIP: Enhancing zero-shot land-use mapping for Sentinel-2 with ground-level prompting

Add code
Dec 11, 2024
Figure 1 for SenCLIP: Enhancing zero-shot land-use mapping for Sentinel-2 with ground-level prompting
Figure 2 for SenCLIP: Enhancing zero-shot land-use mapping for Sentinel-2 with ground-level prompting
Figure 3 for SenCLIP: Enhancing zero-shot land-use mapping for Sentinel-2 with ground-level prompting
Figure 4 for SenCLIP: Enhancing zero-shot land-use mapping for Sentinel-2 with ground-level prompting
Viaarxiv icon

SAT: Spatial Aptitude Training for Multimodal Language Models

Add code
Dec 10, 2024
Figure 1 for SAT: Spatial Aptitude Training for Multimodal Language Models
Figure 2 for SAT: Spatial Aptitude Training for Multimodal Language Models
Figure 3 for SAT: Spatial Aptitude Training for Multimodal Language Models
Figure 4 for SAT: Spatial Aptitude Training for Multimodal Language Models
Viaarxiv icon