Papers with Code 아카이브
Image Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 23
- 평가표
- 93
- 보존된 평가 기록
- 870
Image Generation (synthesis) is the task of generating new images from an existing dataset.
- Unconditional generation refers to generating samples unconditionally from the dataset, i.e. $p(y)$
- Conditional image generation (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.
In this section, you can find state-of-the-art leaderboards for unconditional generation. For conditional generation, and other types of image generations, refer to the subtasks.
<span style="color:grey; opacity: 0.6">( Image credit: StyleGAN )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/deepinsight/insightface
공식 코드ArcFace: Additive Angular Margin Loss for Deep Face Recognition
https://github.com/deeplsd/merkel-podcast-corpus
공식 코드https://github.com/deepmicroscopy/quiltcleaner
공식 코드Model-based Cleaning of the QUILT-1M Pathology Dataset for Text-Conditional Image Synthesis
https://github.com/deepmind/deepmind-research
공식 코드https://github.com/deepmind/dsprites-dataset
공식 코드https://github.com/deepmind/sonnet
공식 코드https://github.com/deepseek-ai/dreamcraft3d
공식 코드DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
https://github.com/deepseek-ai/janus
공식 코드https://github.com/deepvk/metr
공식 코드METR: Image Watermarking with Large Number of Unique Messages
https://github.com/delyan-boychev/pytorch_trainers_interpretability
공식 코드https://github.com/denabazazian/Dual-Domain-Synthesis
공식 코드https://github.com/deng-ai-lab/swformer
공식 코드https://github.com/dengpingfan/fsgan
공식 코드https://github.com/dengyecode/t-former
공식 코드https://github.com/dengyecode/t-former_image_inpainting
공식 코드https://github.com/dependablesystemslab/jujutsu
공식 코드Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks
https://github.com/descriptinc/lyrebird-wav2clip
공식 코드https://github.com/design-bench/design-bench.github.io
공식 코드DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design
https://github.com/design-edit/DesignEdit
공식 코드DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing
https://github.com/devavratTomar/sasan
공식 코드Self-Attentive Spatial Adaptive Normalization for Cross-Modality Domain Adaptation
https://github.com/diaoquesang/BS-LDM
공식 코드https://github.com/diegovalsesia/mmd-ddm
공식 코드Fast Inference in Denoising Diffusion Models via MMD Finetuning
https://github.com/difeigu/radalign
공식 코드RadAlign: Advancing Radiology Report Generation with Vision-Language Concept Alignment
https://github.com/diffusion-classifier/diffusion-classifier
공식 코드https://github.com/diffusion-model-leiden/awesome-diffusion-models-for-tabular-data
공식 코드Diffusion Models for Tabular Data: Challenges, Current Progress, and Future Directions
https://github.com/dimitrismallis/keypointstolandmarks
공식 코드https://github.com/dingsheng-ong/ipr-gan
공식 코드Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack
https://github.com/ditzley/joint-gestures-and-face
공식 코드Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters
https://github.com/divelab/PixelDCN
공식 코드https://github.com/djbradyatopticalsciencesarizona/physicsawaretransformer
공식 코드https://github.com/dlr-mi/atme
공식 코드https://github.com/dniku/perceptual-gradient-networks
공식 코드https://github.com/dolorousrtur/coordinate_based_inpainting
공식 코드Coordinate-based Texture Inpainting for Pose-Guided Image Generation
https://github.com/dome272/paella
공식 코드A Novel Sampling Scheme for Text- and Image-Conditional Image Synthesis in Quantized Latent Spaces
https://github.com/dome272/wuerstchen
공식 코드Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.