Results 131 to 140 of about 24,230 (259)

VividHairEdit: Disentangled Latent Control for High‐Fidelity Hairstyle Transfer via StyleGAN2 Inversion

open access: yesComputer 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

NePO: Neural Point Octrees for Large‐Scale Novel View Synthesis

open access: yesComputer Graphics Forum, EarlyView.
We introduce Neural Point Octrees (NePOs), a scalable radiance field representation that organises point clouds hierarchically for efficient optimisation and rendering of large scale scenes. NePOs enable level of detail selection, joint refinement of appearance and camera poses, and real‐time rendering of hundreds of millions of points.
Noah Lewis   +3 more
wiley   +1 more source

MaX4Zero: Masked Extended Attention for Zero‐Shot Virtual Try‐On In The Wild

open access: yesComputer 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

RotGS: Rotation‐Guided 3D Gaussian Splatting for Turntable Sequences without Structure‐from‐Motion

open access: yesComputer Graphics Forum, EarlyView.
Abstract The field of 3D reconstruction from multi‐view images has advanced rapidly thanks to 3D Gaussian Splatting (3DGS), which enables efficient and photorealistic scene representation. However, optimizing 3DGS requires high‐quality images from various viewpoints with accurate camera poses.
Kyumin Kim   +3 more
wiley   +1 more source

Reconstructing the amplitude and phase of structured light from a single speckle pattern using a deep neural network

open access: yesJPhys Photonics
Directly measuring an optical beam’s full complex field is foundational in optics, but conventional methods typically require interferometric setups. An alternative is to infer the field from an intensity-only speckle pattern produced by a scattering ...
Jonathan L Faller   +2 more
doaj   +1 more source

Final average rankings of algorithms in PSNR, FSIM, and SSIM.

open access: yes
Final average rankings of algorithms in PSNR, FSIM, and SSIM.
Weirui Tang (18196069)   +3 more
core   +1 more source

Statistical Denoising of Transient Rendering

open access: yesComputer Graphics Forum, EarlyView.
Abstract Transient rendering simulates light in motion, measuring the time of flight from the light source to the camera. However, the stochastic nature of Monte Carlo is aggravated in transient rendering, since samples are now spread along the temporal domain.
Oscar Pueyo‐Ciutad   +2 more
wiley   +1 more source

PBR‐Inspired Controllable Diffusion for Image Generation

open access: yesComputer Graphics Forum, EarlyView.
Abstract Despite recent advances in text‐to‐image generation, controlling geometric layout and PBR material properties in synthesized scenes remains challenging. We present a pipeline that first produces a G‐buffer (albedo, normals, depth, roughness, shading, and metallic) from a text prompt and then renders a final image through a PBR‐inspired branch ...
Bowen Xue   +3 more
wiley   +1 more source

Missing Texture Reconstruction Method Based on Perceptually Optimized Algorithm

open access: yesEURASIP Journal on Advances in Signal Processing, 2010
This paper presents a simple and effective missing texture reconstruction method based on a perceptually optimized algorithm. The proposed method utilizes the structural similarity (SSIM) index as a new visual quality measure for reconstructing missing ...
Ogawa Takahiro, Haseyama Miki
doaj  

A Real‐Time Multi‐Scale Neural Representation for Complex Surface Reflectance

open access: yesComputer Graphics Forum, EarlyView.
Abstract Recent machine learning methods have significantly advanced the state of the art in the classic problem of representing surface appearance over angle, space, and scale. The models tend, however, to be relatively heavy compared to traditional fixed‐function representations, making real‐time application challenging.
Heikki Timonen   +2 more
wiley   +1 more source

Home - About - Disclaimer - Privacy