Papers with Code 아카이브
Texture Synthesis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
The fundamental goal of example-based Texture Synthesis is to generate a texture, usually larger than the input, that faithfully captures all the visual characteristics of the exemplar, yet is neither identical to it, nor exhibits obvious unnatural looking artifacts.
Source: Non-Stationary Texture Synthesis by Adversarial Expansion
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
User-Controllable Multi-Texture Synthesis with Generative Adversarial Networks
Re-Identification Supervised Texture Generation
Texture Synthesis Guided Deep Hashing for Texture Image Retrieval
Context-Aware Text-Based Binary Image Stylization and Synthesis
Second-order Democratic Aggregation
Texture Mixing by Interpolating Deep Statistics via Gaussian Models
Non-Stationary Texture Synthesis by Adversarial Expansion
Learning the Synthesizability of Dynamic Texture Samples
Multiscale Sparse Microcanonical Models
Improved Style Transfer by Respecting Inter-layer Correlations
Texture Synthesis with Recurrent Variational Auto-Encoder
On Using Backpropagation for Speech Texture Generation and Voice Conversion
Geometry Guided Adversarial Facial Expression Synthesis
Image Inpainting for High-Resolution Textures using CNN Texture Synthesis
GANosaic: Mosaic Creation with Generative Texture Manifolds
Fashioning with Networks: Neural Style Transfer to Design Clothes
A survey of exemplar-based texture synthesis
Synthesis of Near-regular Natural Textures
Graphcut Texture Synthesis for Single-Image Superresolution
Two-Stream Convolutional Networks for Dynamic Texture Synthesis
TextureGAN: Controlling Deep Image Synthesis with Texture Patches
Towards Metamerism via Foveated Style Transfer
Learning Texture Manifolds with the Periodic Spatial GAN
A Procedural Texture Generation Framework Based on Semantic Descriptions
Perception Driven Texture Generation
Diversified Texture Synthesis with Feed-forward Networks
Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses
Super-resolution Using Constrained Deep Texture Synthesis
Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
On Random Weights for Texture Generation in One Layer Neural Networks
Awesome Typography: Statistics-Based Text Effects Transfer
Texture Synthesis with Spatial Generative Adversarial Networks
Bayesian Modeling of Motion Perception using Dynamical Stochastic Textures
Example-Based Image Synthesis via Randomized Patch-Matching
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.