ArcFace
PulseAugur coverage of ArcFace — every cluster mentioning ArcFace across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
Humanoid robot head integrates AI for natural receptionist interactions
Researchers have developed an articulated humanoid robot head designed for a receptionist role, aiming to improve natural human-robot interactions. This head features 21 degrees of freedom for realistic expressions and …
-
MGFace pipeline improves masked face identification accuracy
Researchers have developed MGFace, a novel pipeline for face identification that improves accuracy when faces are partially occluded by masks. MGFace intelligently routes similarity computations by first detecting if a …
-
MGFace pipeline improves masked face identification accuracy
Researchers have developed MGFace, a new pipeline for face identification that improves accuracy for masked faces. The system conditionally routes similarity computations based on whether a face is masked, applying a ma…
-
LILAC framework enables multi-concept customization of diffusion models
Researchers have introduced LILAC, a novel framework for personalizing text-to-image diffusion models. LILAC addresses the challenge of rendering multiple specific subjects coherently by composing independently trained …
-
New LoRA model preserves identity in reference-to-video generation
A new LoRA model, Alissonerdx/LTX-Best-Face-ID, has been released for LTX-2.3, enabling identity-preserving reference-to-video generation. This model allows users to input a reference photo of a person and a text prompt…
-
New Q-Margin loss enhances biometric verification with probabilistic margins
Researchers have introduced Q-Margin, a novel $\alpha$-divergence loss function designed to improve biometric verification systems. This new loss function encodes a principled probabilistic margin directly into prior pr…
-
New AI tool Envisage visualizes rhinoplasty outcomes with novel evaluation metric
Researchers have developed Envisage, a new pipeline for visualizing the intended outcomes of rhinoplasty surgery using diffusion-based generative editing. This system is designed to provide localized edits and includes …
-
New synthetic dataset evaluates face recognition systems
Researchers have introduced CounterFace, a novel synthetic dataset designed for the fine-grained evaluation of face recognition systems. This dataset comprises 11,821 counterfactual face pairs across 20 facial attribute…
-
New frameworks and benchmarks advance audio-visual generation
Researchers have introduced OmniCustom, a framework for customizing both video identity and audio timbre simultaneously from reference images and audio. This DiT-based model uses separate LoRA modules for identity and t…