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.
Incorporating long-range consistency in CNN-based texture generation
Texture Synthesis Using Shallow Convolutional Networks with Random Filters
Patch-based Texture Synthesis for Image Inpainting
Texture Synthesis Through Convolutional Neural Networks and Spectrum Constraints
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis
A note on the evaluation of generative models
Texture Modelling with Nested High-order Markov-Gibbs Random Fields
Generative Image Modeling Using Spatial LSTMs
Texture Synthesis Using Convolutional Neural Networks
Automatic Objects Removal for Scene Completion
Facial Feature Point Detection: A Comprehensive Survey
Structure Preserving Large Imagery Reconstruction
Periodicity Extraction using Superposition of Distance Matching Function and One-dimensional Haar Wavelet Transform
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.