arXiv:2605.22311v2 Announce Type: replace Abstract: Identity-conditioned diffusion models enable high-quality and identity-consistent face generation, but they also raise severe privacy concerns, as...
arXiv:2511.05575v2 Announce Type: replace Abstract: Diffusion-based approaches have recently achieved strong results in face swapping, offering improved visual quality over traditional GAN-based meth...
The paper introduces Semantic Boundary Predictor (SBP), an inference‑time framework that improves demographic fairness in synthetic face generation by applying a single, one‑shot intervention during reverse denoising. SBP learns linear semantic boundaries from late‑stage latent representations and applies them only at the initial noisy latent, leaving the rest of the diffusion process unchanged. Experiments on CelebA‑HQ show significant reductions in fairness disparity—98% for gender, 95% for binary race, and 15% for four‑class race—while preserving image quality across demographic groups.
The paper introduces EC²Face, a multimodal face synthesis framework that enhances semantic alignment by combining Explicit Conditional Consistency Guidance (ECCG) and Long‑Tail Adaptive Flow Matching (LAFM). ECCG enforces pixel‑level consistency between generated faces, textual descriptions, and semantic masks, while a temporal dynamic modulation adjusts supervision strength over diffusion timesteps. LAFM reweights spatial optimization signals according to attribute frequency, improving rare attribute synthesis without adding inference overhead. Experiments demonstrate that EC²Face outperforms baselines, achieving a 29.38% improvement in mask accuracy for rare attributes.
arXiv:2607. 28936v1 Announce Type: cross Abstract: Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space.
arXiv:2610.09450v1 Announce Type: new Abstract: Pixel-space diffusion models avoid the lossy VAE of latent models, which suggests an advantage on downstream tasks where fine-grained detail matters. W...
arXiv:2606. 11615v1 Announce Type: cross Abstract: The widespread adoption of face recognition (FR) technologies raises serious privacy concerns, as facial data can be exploited without consent.
arXiv:2505.23462v2 Announce Type: replace Abstract: Blind face restoration from low-quality images is a challenging task that requires not only high-fidelity image reconstruction, but also preservati...
The paper introduces the Deepfake Face Artifact Taxonomy (DFAT) and uses it to create both general-purpose and model-specific training materials for detecting deepfake face images. An online experiment with 524 participants tested detection accuracy across five generative models—three GANs, one diffusion model, and one multimodal large language model (GPT‑5)—showing that detection performance varies strongly by model and that model‑specific training yields greater gains than general training. A five‑month follow‑up with 342 participants revealed stable detection accuracy and no increase in perceived stress, suggesting the training’s durability.
ScoreMix is a self‑contained synthetic data generation method that improves recognition tasks by mixing class‑conditioned scores along reverse diffusion trajectories, thereby creating hard synthetic samples without external resources. The approach shows that selecting classes far apart in the discriminator’s embedding space yields larger performance gains, up to 3% more improvement than proximity‑based selection. Across eight public face recognition benchmarks, ScoreMix boosts accuracy by up to 7 percentage points, demonstrating robustness and practicality without hyperparameter tuning.
UltraDiff is a new framework for high‑resolution image generation with Latent Diffusion Models that tackles the trade‑off between computational cost and fidelity caused by latent compression. It jointly learns latent diffusion and then distills a marginal score using a dual‑branch DiT called MixTeacher, which models both f8 and f32 distributions and resolves compressed‑space ambiguity with high‑fidelity priors. Vector‑field distillation in the native f32 space forces the student model to learn the teacher’s conditional expectation, filtering out compression artifacts and achieving f8‑level quality while retaining f32 efficiency—generating a 2K image in 6.2 seconds on a single A100 GPU, over 40× faster than the f8 baseline.
arXiv:2609.39657v1 Announce Type: new Abstract: Distilling pretrained foundation models into an autoencoder bottleneck improves latent diffusability, enabling diffusion models to converge faster and...