Search Results for author: Giuseppe Vecchio

Found 7 papers, 3 papers with code

StableMaterials: Enhancing Diversity in Material Generation via Semi-Supervised Learning

no code implementations13 Jun 2024 Giuseppe Vecchio

This distillation approach aligns the distribution of the generated materials with that of image textures from an SDXL model, enabling the generation of novel materials that are not present in the initial training dataset.

Image Generation

ControlMat: A Controlled Generative Approach to Material Capture

no code implementations4 Sep 2023 Giuseppe Vecchio, Rosalie Martin, Arthur Roullier, Adrien Kaiser, Romain Rouffet, Valentin Deschaintre, Tamy Boubekeur

Our generative approach further permits exploration of a variety of materials which could correspond to the input image, mitigating the unknown lighting conditions.

MatFuse: Controllable Material Generation with Diffusion Models

1 code implementation CVPR 2024 Giuseppe Vecchio, Renato Sortino, Simone Palazzo, Concetto Spampinato

Creating high-quality materials in computer graphics is a challenging and time-consuming task, which requires great expertise.

SVBRDF Estimation

MeT: A Graph Transformer for Semantic Segmentation of 3D Meshes

no code implementations3 Jul 2023 Giuseppe Vecchio, Luca Prezzavento, Carmelo Pino, Francesco Rundo, Simone Palazzo, Concetto Spampinato

Polygonal meshes have become the standard for discretely approximating 3D shapes, thanks to their efficiency and high flexibility in capturing non-uniform shapes.

Segmentation Semantic Segmentation

SurfaceNet: Adversarial SVBRDF Estimation from a Single Image

2 code implementations ICCV 2021 Giuseppe Vecchio, Simone Palazzo, Concetto Spampinato

In this paper we present SurfaceNet, an approach for estimating spatially-varying bidirectional reflectance distribution function (SVBRDF) material properties from a single image.

Generative Adversarial Network SVBRDF Estimation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.