We introduce the physically based neural BRDF, a novel continuous representation for material appearance based on neural fields. Our model accurately performs real‐world material reconstruction, generation and editing, while uniquely enhancing the physical accuracy of neural BRDFs via three key aspects: energy conservation, Helmholtz reciprocity and ...
C. Zhou +8 more
wiley +1 more source
Assessment of rotational dose perturbations in SBRT: A radiomic-dosiomic predictive model based on the structural similarity index measure. [PDF]
Qi R +5 more
europepmc +1 more source
Single Line Drawing Generation via Semantics‐Driven Optimization
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
Assessment of Deep Learning-Generated Ultra-Widefield Fluorescein Angiography From Fundus Images in Diabetic Retinopathy. [PDF]
Park SE, Kim JH, Lee SH, Ra H, Baek J.
europepmc +1 more source
Volumetric Inverse Rendering via Neural Radiative Transfer
Abstract Volumetric inverse rendering seeks to recover the optical properties of participating media from images. Existing approaches either rely on differentiable stochastic light transport simulation, which require substantial algorithmic effort, or use simplified models that fail to capture global illumination.
Ntumba Elie Nsampi +4 more
wiley +1 more source
Image stitching for probe-based confocal laser endomicroscopy via a motion consistency constraint. [PDF]
Hao Z +7 more
europepmc +1 more source
Beyond Spherical Harmonics: Rethinking Appearance Models for Radiance Reconstruction
Abstract View‐dependent appearance modeling remains a challenging problem in novel‐view synthesis and reconstruction. Accurately representing complex angular effects often requires substantial memory and computational resources. For new learning‐based methods, a common approach is to rely on Spherical Harmonics (SH).
Ewa Miazga, Jorge Condor, Piotr Didyk
wiley +1 more source
Super-Resolution Reconstruction of Reservoir Core CT Images via GAN: Advancing Energy Extraction Accuracy. [PDF]
Lv X, Li Y.
europepmc +1 more source
FlowGS: Controlling Information Flow for Graph‐Based Interaction in 3D Gaussian Splatting
Abstract 3D Gaussian Splatting (3DGS) has recently enabled real‐time, high‐quality novel view synthesis. However, its formulation treats each Gaussian independently, lacking explicit information exchange between neighboring elements and limiting its ability to capture local structure.
T. Jia, R. Sun, W. Shi
wiley +1 more source
Boosting underwater image quality: a deep learning approach to denoising and enhancement. [PDF]
Ali N +5 more
europepmc +1 more source

