https://github.com/yisuanwang/idea23d
공식 코드Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs
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/yitongx/sinerf
공식 코드SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstruction
https://github.com/yixuan/temperflow
공식 코드Efficient Multimodal Sampling via Tempered Distribution Flow
https://github.com/yiyanxu/diffrec
공식 코드https://github.com/yiyanxu/pigeon
공식 코드https://github.com/yizhiwang96/deepvecfont
공식 코드DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning
https://github.com/yjhboy/hyper3dg
공식 코드https://github.com/ykykyk112/STIG
공식 코드https://github.com/yluestc/derain
공식 코드https://github.com/ymxbj/TexGaussian
공식 코드TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting
https://github.com/ymxbj/VecFontSDF
공식 코드https://github.com/yonatanbitton/wysiwyr
공식 코드What You See is What You Read? Improving Text-Image Alignment Evaluation
https://github.com/yonghaoxu/txt2img-mhn
공식 코드Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks
https://github.com/yongliang-wu/doco
공식 코드Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
https://github.com/yongliang-wu/unlearn-DoCoPreG
공식 코드Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
https://github.com/yongquan-qu/slams
공식 코드https://github.com/yongqyu/TCN
공식 코드https://github.com/yonseivnl/cmota
공식 코드Story Visualization by Online Text Augmentation with Context Memory
https://github.com/yoshihidesawada/CompGAN
공식 코드Study of Deep Generative Models for Inorganic Chemical Compositions
https://github.com/younggeun-kim/Styleformer
공식 코드Styleformer: Transformer based Generative Adversarial Networks with Style Vector
https://github.com/yousia/lgr_ad
공식 코드https://github.com/youyuge34/PI-REC
공식 코드PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain
https://github.com/ypxie/HDGan
공식 코드Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network
https://github.com/yqx7150/EBMRec
공식 코드https://github.com/yqx7150/ivan
공식 코드Variable Augmented Network for Invertible Modality Synthesis-Fusion
https://github.com/yqx7150/shgm
공식 코드Generative Modeling in Structural-Hankel Domain for Color Image Inpainting
https://github.com/yqx7150/swarm
공식 코드Physics-informed DeepCT: Sinogram Wavelet Decomposition Meets Masked Diffusion
https://github.com/ysy31415/unipaint
공식 코드Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Model
https://github.com/yuangan/eat_code
공식 코드Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation
https://github.com/yuangan/silencer
공식 코드https://github.com/yuangpeng/dreambench_plus
공식 코드DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation
https://github.com/yuanze-lin/Learnable_Regions
공식 코드https://github.com/yuanzhengthu/handDrawnPAAImages
공식 코드Self-similarity-based super-resolution of photoacoustic angiography from hand-drawn doodles
https://github.com/yuanzhi-zhu/diffpir
공식 코드Denoising Diffusion Models for Plug-and-Play Image Restoration
https://github.com/yuchuantian/u-dit
공식 코드U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
https://github.com/yuchuantian/u-repa
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.