CVPR 2023 accepted papers on Image generation
274 of the 2,359 papers accepted at CVPR 2023 (11.6%) are on Image generation, compared with 9.3% at CVPR 2022. They fall into 7 topics.
See CVPR 2023 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Image restoration · 71 papers
- Efficient Frequency Domain-Based Transformers for High-Quality Image Deblurring (387 citations)
- Learning a Simple Low-Light Image Enhancer From Paired Low-Light Instances (371 citations)
- Efficient and Explicit Modelling of Image Hierarchies for Image Restoration (292 citations)
- Generative Diffusion Prior for Unified Image Restoration and Enhancement (275 citations)
- RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors (237 citations)
- Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement (200 citations)
- DynIBaR: Neural Dynamic Image-Based Rendering (172 citations)
- WIRE: Wavelet Implicit Neural Representations (172 citations)
- Zero-Shot Noise2Noise: Efficient Image Denoising Without Any Data (172 citations)
- Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions (167 citations)
- Low-Light Image Enhancement via Structure Modeling and Guidance (158 citations)
- Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising (132 citations)
and 59 more in the interactive map.
Autoregressive and latent generation · 64 papers
- Towards Universal Fake Image Detectors That Generalize Across Generative Models (381 citations)
- Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures (326 citations)
- All Are Worth Words: A ViT Backbone for Diffusion Models (256 citations)
- EDGE: Editable Dance Generation From Music (238 citations)
- High-Resolution Image Reconstruction With Latent Diffusion Models From Human Brain Activity (236 citations)
- Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection (191 citations)
- LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation (172 citations)
- Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models (169 citations)
- Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild (139 citations)
- Seeing Beyond the Brain: Conditional Diffusion Model With Sparse Masked Modeling for Vision Decoding (129 citations)
- DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation (128 citations)
- Semantic-Conditional Diffusion Networks for Image Captioning (120 citations)
and 52 more in the interactive map.
Editing and style transfer · 57 papers
- InstructPix2Pix: Learning To Follow Image Editing Instructions (1,395 citations)
- Imagic: Text-Based Real Image Editing With Diffusion Models (734 citations)
- Paint by Example: Exemplar-Based Image Editing With Diffusion Models (347 citations)
- Inversion-Based Style Transfer With Diffusion Models (345 citations)
- BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models (251 citations)
- RODIN: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion (205 citations)
- DCFace: Synthetic Face Generation With Dual Condition Diffusion Model (150 citations)
- Collaborative Diffusion for Multi-Modal Face Generation and Editing (146 citations)
- Person Image Synthesis via Denoising Diffusion Model (127 citations)
- EDICT: Exact Diffusion Inversion via Coupled Transformations (122 citations)
- DiffSwap: High-Fidelity and Controllable Face Swapping via 3D-Aware Masked Diffusion (101 citations)
- GP-VTON: Towards General Purpose Virtual Try-On via Collaborative Local-Flow Global-Parsing Learning (97 citations)
and 45 more in the interactive map.
Super-resolution · 29 papers
- Activating More Pixels in Image Super-Resolution Transformer (1,108 citations)
- Implicit Diffusion Models for Continuous Super-Resolution (272 citations)
- N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution (222 citations)
- Omni Aggregation Networks for Lightweight Image Super-Resolution (207 citations)
- Spatial-Frequency Mutual Learning for Face Super-Resolution (118 citations)
- CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution (93 citations)
- Super-Resolution Neural Operator (77 citations)
- Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution (73 citations)
- Perception-Oriented Single Image Super-Resolution Using Optimal Objective Estimation (59 citations)
- Guided Depth Super-Resolution by Deep Anisotropic Diffusion (58 citations)
- CutMIB: Boosting Light Field Super-Resolution via Multi-View Image Blending (51 citations)
- Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution (48 citations)
and 17 more in the interactive map.
Text-to-image diffusion · 28 papers
- DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation (2,183 citations)
- Magic3D: High-Resolution Text-to-3D Content Creation (813 citations)
- Align Your Latents: High-Resolution Video Synthesis With Latent Diffusion Models (679 citations)
- NULL-Text Inversion for Editing Real Images Using Guided Diffusion Models (678 citations)
- Multi-Concept Customization of Text-to-Image Diffusion (627 citations)
- Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation (582 citations)
- GLIGEN: Open-Set Grounded Text-to-Image Generation (554 citations)
- Open-Vocabulary Panoptic Segmentation With Text-to-Image Diffusion Models (354 citations)
- SmartBrush: Text and Shape Guided Object Inpainting With Diffusion Model (215 citations)
- Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models (196 citations)
- Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting (158 citations)
- SpaText: Spatio-Textual Representation for Controllable Image Generation (156 citations)
and 16 more in the interactive map.
Fast diffusion sampling · 14 papers
- On Distillation of Guided Diffusion Models (302 citations)
- Ambiguous Medical Image Segmentation Using Diffusion Models (210 citations)
- Leapfrog Diffusion Model for Stochastic Trajectory Prediction (209 citations)
- Post-Training Quantization on Diffusion Models (138 citations)
- Wavelet Diffusion Models Are Fast and Scalable Image Generators (133 citations)
- Diffusion Probabilistic Model Made Slim (94 citations)
- Class-Balancing Diffusion Models (41 citations)
- Real-Time Controllable Denoising for Image and Video (28 citations)
- Self-Guided Diffusion Models (22 citations)
- Unite and Conquer: Plug & Play Multi-Modal Synthesis Using Diffusion Models (15 citations)
- Lookahead Diffusion Probabilistic Models for Refining Mean Estimation (8 citations)
- Towards Practical Plug-and-Play Diffusion Models (7 citations)
and 2 more in the interactive map.
GANs · 11 papers
- Scaling Up GANs for Text-to-Image Synthesis (392 citations)
- GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis (164 citations)
- Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration (31 citations)
- KD-DLGAN: Data Limited Image Generation via Knowledge Distillation (27 citations)
- AdaptiveMix: Improving GAN Training via Feature Space Shrinkage (26 citations)
- Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond (22 citations)
- Discriminator-Cooperated Feature Map Distillation for GAN Compression (19 citations)
- GLeaD: Improving GANs With a Generator-Leading Task (12 citations)
- Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences Between Pretrained Generative Models (8 citations)
- Spider GAN: Leveraging Friendly Neighbors To Accelerate GAN Training (2 citations)
- Sequential Training of GANs Against GAN-Classifiers Reveals Correlated "Knowledge Gaps" Present Among Independently Trained GAN Instances (1 citation)