Research map / Image generation / GANs
Dynamic Facial Expression Generation on Hilbert Hypersphere With Conditional Wasserstein Generative Adversarial Nets
Naima Otberdout, Mohamed Daoudi, Anis Kacem, Lahoucine Ballihi, Stefano Berretti
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add identity loss L_id to TextureGAN (ablation) | full model · Oulu-CASIA | ACD: 0.0193 -> 0.016 | Improved |
| add identity loss L_id to TextureGAN (ablation) | full model · Oulu-CASIA | PSNR: 26.05 -> 24.443 | Hurt |
| add reconstruction loss on S to MotionGAN (ablation) | full model · Oulu-CASIA | PSNR: 24.180 -> 24.443 | Improved |
| add reconstruction loss on S to MotionGAN (ablation) | full model · Oulu-CASIA | SSIM: 0.886 -> 0.891 | Improved |
| add reconstruction loss on S to MotionGAN (ablation) | full model · Oulu-CASIA | ACD: 0.017 -> 0.016 | Improved |
| use ground truth landmarks instead of MotionGAN-generated ones (ablation) | full model · Oulu-CASIA | ACD-I: 0.107 -> 0.10 | Improved |
| use ground truth landmarks instead of MotionGAN-generated ones (ablation) | full model · Oulu-CASIA | PSNR: 24.443 -> 25.98 | Improved |
| generate with MotionGAN+TextureGAN instead of VGAN | video generation · MUG | Inception Score: 3.24 -> 3.52 | Improved |
| generate with MotionGAN+TextureGAN instead of VGAN | video generation · MUG | PSNR: 20.98 -> 25.90 | Improved |
| generate with MotionGAN+TextureGAN instead of MoCoGAN | video generation · MUG | ACD: 0.045 -> 0.011 | Improved |
| generate with ours instead of VGAN, LSTM recognition | video generation · MUG expression recognition | accuracy (%): 45.28 -> 69.82 | Improved |
| augment training data with MotionGAN videos (x10) | LSTM expression classifier · CASIA | accuracy (%): 87.5 -> 92.7 | Improved |
Closest papers by meaning
- Sparse to Dense Dynamic 3D Facial Expression Generation (CVPR 2022 · similarity 0.90)
- GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV 2018 · similarity 0.87)
- GANimation: One-Shot Anatomically Consistent Facial Animation (IJCV 2019 · similarity 0.87)
- Joint Pose and Expression Modeling for Facial Expression Recognition (CVPR 2018 · similarity 0.87)
- DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation (AAAI 2025 · similarity 0.85)
- 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
