Face Reenactment


Face reenactment is the process of transferring facial expressions from one person to another in videos.

Detecting Localized Deepfake Manipulations Using Action Unit-Guided Video Representations

Add code
Mar 28, 2025
Viaarxiv icon

Two-Stream Spatial-Temporal Transformer Framework for Person Identification via Natural Conversational Keypoints

Add code
Feb 28, 2025
Viaarxiv icon

GHOST 2.0: generative high-fidelity one shot transfer of heads

Add code
Feb 26, 2025
Figure 1 for GHOST 2.0: generative high-fidelity one shot transfer of heads
Figure 2 for GHOST 2.0: generative high-fidelity one shot transfer of heads
Figure 3 for GHOST 2.0: generative high-fidelity one shot transfer of heads
Figure 4 for GHOST 2.0: generative high-fidelity one shot transfer of heads
Viaarxiv icon

Generating and Detecting Various Types of Fake Image and Audio Content: A Review of Modern Deep Learning Technologies and Tools

Add code
Jan 07, 2025
Viaarxiv icon

TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model

Add code
Oct 14, 2024
Figure 1 for TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model
Figure 2 for TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model
Figure 3 for TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model
Figure 4 for TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model
Viaarxiv icon

G3FA: Geometry-guided GAN for Face Animation

Add code
Aug 23, 2024
Figure 1 for G3FA: Geometry-guided GAN for Face Animation
Figure 2 for G3FA: Geometry-guided GAN for Face Animation
Figure 3 for G3FA: Geometry-guided GAN for Face Animation
Figure 4 for G3FA: Geometry-guided GAN for Face Animation
Viaarxiv icon

EmojiHeroVR: A Study on Facial Expression Recognition under Partial Occlusion from Head-Mounted Displays

Add code
Oct 04, 2024
Figure 1 for EmojiHeroVR: A Study on Facial Expression Recognition under Partial Occlusion from Head-Mounted Displays
Figure 2 for EmojiHeroVR: A Study on Facial Expression Recognition under Partial Occlusion from Head-Mounted Displays
Figure 3 for EmojiHeroVR: A Study on Facial Expression Recognition under Partial Occlusion from Head-Mounted Displays
Figure 4 for EmojiHeroVR: A Study on Facial Expression Recognition under Partial Occlusion from Head-Mounted Displays
Viaarxiv icon

Anchored Diffusion for Video Face Reenactment

Add code
Jul 21, 2024
Figure 1 for Anchored Diffusion for Video Face Reenactment
Figure 2 for Anchored Diffusion for Video Face Reenactment
Figure 3 for Anchored Diffusion for Video Face Reenactment
Figure 4 for Anchored Diffusion for Video Face Reenactment
Viaarxiv icon

Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion

Add code
Aug 01, 2024
Figure 1 for Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion
Figure 2 for Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion
Figure 3 for Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion
Figure 4 for Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion
Viaarxiv icon

DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion

Add code
Sep 25, 2024
Figure 1 for DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion
Figure 2 for DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion
Figure 3 for DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion
Figure 4 for DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion
Viaarxiv icon