Deep Texture

Deep texture research focuses on generating, analyzing, and utilizing highly detailed textures in digital images and 3D models, aiming for realism and efficiency in various applications. Current efforts involve developing novel algorithms, such as recursive optimization and part-aware stylization methods, to create intricate textures from various inputs including text descriptions and 3D meshes. This field is crucial for advancing computer graphics, virtual reality, and image authenticity verification, with applications ranging from creating realistic virtual environments to detecting computer-generated imagery. The development of large-scale, high-fidelity datasets is also a key area of focus, enabling improved model training and evaluation.

Papers

March 22, 2024

TexRO: Generating Delicate Textures of 3D Models by Recursive Optimization
Jinbo Wu, Xing Liu, Chenming Wu, Xiaobo Gao, Jialun Liu, Xinqi Liu, Chen Zhao, Haocheng Feng, Errui Ding, Jingdong Wang
3D Model 3D Mesh Recursive Algorithm Texture Generation Texture Quality UV Texture Deep Texture

August 31, 2023

Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details
Inwoo Hwang, Hyeonwoo Kim, Young Min Kim
Image Stylization Part Aware High Fidelity Texture Texture Information Realistic Texture Deep Texture

October 14, 2022

DART: Articulated Hand Model with Diverse Accessories and Rich Textures
Daiheng Gao, Yuliang Xiu, Kailin Li, Lixin Yang, Feng Wang, Peng Zhang, Bang Zhang, Cewu Lu, Ping Tan
Arbitrary Object Morphable Model Hand Object Hand Datasets Hand Model Hand Image Generation Deep Texture

September 7, 2022

Joint Learning of Deep Texture and High-Frequency Features for Computer-Generated Image Detection
Qiang Xu, Shan Jia, Xinghao Jiang, Tanfeng Sun, Zhe Wang, Hong Yan
Convolutional Neural Network Generative Adversarial Network Joint Learning Frequency Feature Texture Recognition Deep Texture

April 18, 2022

Inductive Biases for Object-Centric Representations in the Presence of Complex Textures
Samuele Papa, Ole Winther, Andrea Dittadi
Inductive Bias Segmentation Performance Speech Presence Object Centric Representation Segmentation Quality Neural Style Transfer Deep Texture Compound Figure Separation

Deep Texture

Papers

TexRO: Generating Delicate Textures of 3D Models by Recursive Optimization

Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details

DART: Articulated Hand Model with Diverse Accessories and Rich Textures

Joint Learning of Deep Texture and High-Frequency Features for Computer-Generated Image Detection

Inductive Biases for Object-Centric Representations in the Presence of Complex Textures