Results 161 to 170 of about 2,911,065 (235)
Computer Graphics Forum, EarlyView.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
Camera Fingerprint estimation with a Generative Adversarial Network (GAN)
Electronic Imaging, 2021 openaire +2 more sources
Adaptive Sampling for BRDF Acquisition
Computer Graphics Forum, EarlyView.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
MaX4Zero: Masked Extended Attention for Zero‐Shot Virtual Try‐On In The Wild
Computer Graphics Forum, EarlyView.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
Style Brush: Guided Style Transfer for 3D Objects
Computer Graphics Forum, EarlyView.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
Single Line Drawing Generation via Semantics‐Driven Optimization
Computer Graphics Forum, EarlyView.We present a method for automatically generating single‐line drawings in vector format, guided by a text prompt or an input image. Our approach leverages score distillation sampling to optimize the parameters of a uniform rational B‐spline (URBS) curve, ensuring that the drawing consists of a single continuous stroke by design.
Tanguy Magne +3 more
wiley +1 more source
Generative Adversarial Networks (GANs): A Survey on Network Traffic Generation
International Journal of Machine Learning and Computing, 2022 openaire +1 more source
FaceIt: Real‐Time On‐Device Identity‐Preserving Portrait Animation
Computer Graphics Forum, EarlyView.A real‐time, on‐device algorithm for animating a single portrait image using detailed facial expressions and motions from a driving video achieving visual quality that can outperform even techniques with significantly higher computational overhead. Abstract Recently, significant progress has been made in generating expressive and temporally coherent ...
M. Dvorožňák +7 more
wiley +1 more source
Rendering Synthetic Defects for Learning‐Based Industrial Inspection
Computer Graphics Forum, EarlyView.Abstract Computer vision increasingly uses synthetic data from physically based rendering to supplement limited real‐world datasets. In industrial inspection, defect data is scarce and the rendering pipeline is explicitly controlled, and synthetic defect generation therefore becomes a dataset design problem.
Runzhou Mao +5 more
wiley +1 more source
ResEdit: Residual embeddings for precise generative image editing
Computer Graphics Forum, EarlyView.Abstract Conditional diffusion image generators can be repurposed for editing through inversion, without the need for large‐scale paired fine‐tuning data. However, producing high‐quality, targeted edits while maintaining image identity and global consistency remains challenging, as weakly conditioned inversion often embeds conflicting image features ...
Canberk Baykal +6 more
wiley +1 more source