mzLearn as a data-driven LC/MS signal detection algorithm that enables pre-trained generative models for untargeted metabolomics. [PDF]
Pirhaji L +5 more
europepmc +1 more source
VividHairEdit is an advanced StyleGAN2 inversion system for high‐fidelity hair transfer and editing. Our system features improved structural integration, vibrant appearance representation, and optimized latent code selection, achieving superior generation quality and usability. A user‐friendly sketch interface enables precise modifications that reflect
Eunyeong Choi, Sihun Jin, Dongjoon Kim
wiley +1 more source
Symmetry-Driven Multimodal Adversarial Attacks: An Information-Theoretic Perspective on Cross-Modal Invariance and Robustness. [PDF]
Wei J, Wang X, Xu L, Li Y.
europepmc +1 more source
Adaptive Sampling for BRDF Acquisition
We propose a data‐driven adaptive sampling strategy that predicts the optimal sampling pattern and count for BRDF acquisition from a single image, reducing capture time while preserving quality. Abstract The bidirectional reflectance distribution function (BRDF) describes the ratio of incoming radiance to outgoing radiance for all possible pairs of ...
Behnaz Kavoosighafi +3 more
wiley +1 more source
Data-driven global ocean model resolving atmospherically forced ocean dynamics. [PDF]
Kim JH +4 more
europepmc +1 more source
MaX4Zero: Masked Extended Attention for Zero‐Shot Virtual Try‐On In The Wild
Max4Zero is a zero‐shot, training‐free virtual try‐on method that leverages diffusion priors and extended attention for accurate garment transfer. By warping reference garments and mitigating texture sticking, it achieves superior fidelity, garment preservation and identity consistency over state‐of‐the‐art methods without additional training ...
Nadav Orzech +4 more
wiley +1 more source
Automated knee MRI segmentation with KneeSeg-U for cartilage and bone extraction using an unsupervised deep learning framework. [PDF]
Rajeena PPF +9 more
europepmc +1 more source
Style Brush: Guided Style Transfer for 3D Objects
We introduce Style Brush, a guided 3D style‐transfer method for textured meshes that provides precise creative control. It supports the use of multiple style images, smooth transitions and intuitive guidance, producing visually appealing textures that follow user intent as we demonstrate in our user study and results. Abstract We introduce Style Brush,
Áron Samuel Kovács +2 more
wiley +1 more source
Hybrid GNN-LSTM defense with differential privacy and secure multi-party computation for edge-optimized neuromorphic autonomous systems. [PDF]
Rekik S, Mehmood S.
europepmc +1 more source
High‐Gloss SVBRDF Capture Using Bounce Light
Abstract Reflectance capture aims at the visual reproduction of an object under varying illumination. Past works differ substantially in their experimental overhead, from single‐ or few‐image approaches, that employ significant (often learned) priors at the expense of biased reconstructions, to more accurate approaches that tend to be time‐consuming ...
Tomáš Iser +2 more
wiley +1 more source

