Papers with Code 아카이브
2D Semantic Segmentation task 3 (25 classes)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 1
- 보존된 평가 기록
- 6
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
RealitySummary: Exploring On-Demand Mixed Reality Text Summarization and Question Answering using Large Language Models
NAF-DPM: A Nonlinear Activation-Free Diffusion Probabilistic Model for Document Enhancement
DECDM: Document Enhancement using Cycle-Consistent Diffusion Models
DocDiff: Document Enhancement via Residual Diffusion Models
TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles
LP-IOANet: Efficient High Resolution Document Shadow Removal
Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement
Effective semantic segmentation in Cataract Surgery: What matters most?
Evaluating Deep Neural Networks for Image Document Enhancement
Light-weight Document Image Cleanup using Perceptual Loss
DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement
CaDIS: Cataract Dataset for Image Segmentation
DeepOtsu: Document Enhancement and Binarization using Iterative Deep Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.