ICML 2024 accepted papers on Image generation
135 of the 2,610 papers accepted at ICML 2024 (5.2%) are on Image generation, compared with 4.1% at ICML 2023. They fall into 7 topics.
See ICML 2024 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
Fast diffusion sampling · 48 papers
- DiffDA: a Diffusion model for weather-scale Data Assimilation (10 citations)
- Dirichlet Flow Matching with Applications to DNA Sequence Design (10 citations)
- Accelerating Parallel Sampling of Diffusion Models (4 citations)
- Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (4 citations)
- Guidance with Spherical Gaussian Constraint for Conditional Diffusion (4 citations)
- DITTO: Diffusion Inference-Time T-Optimization for Music Generation (3 citations)
- Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes (3 citations)
- AdsorbDiff: Adsorbate Placement via Conditional Denoising Diffusion (2 citations)
- Directly Denoising Diffusion Models (2 citations)
- Listening to the noise: Blind Denoising with Gibbs Diffusion (2 citations)
- Particle Denoising Diffusion Sampler (2 citations)
- Stochastic Interpolants with Data-Dependent Couplings (2 citations)
and 36 more in the interactive map.
Autoregressive and latent generation · 39 papers
- NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models (20 citations)
- Diffusion Language Models Are Versatile Protein Learners (18 citations)
- Proteus: Exploring Protein Structure Generation for Enhanced Designability and Efficiency (18 citations)
- Protein Conformation Generation via Force-Guided SE(3) Diffusion Models (12 citations)
- Fast Timing-Conditioned Latent Audio Diffusion (7 citations)
- MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data (5 citations)
- Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion (4 citations)
- Behavior Generation with Latent Actions (3 citations)
- Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers (3 citations)
- Adaptive Sampling of k-Space in Magnetic Resonance for Rapid Pathology Prediction (2 citations)
- Floating Anchor Diffusion Model for Multi-motif Scaffolding (2 citations)
- Quantum Implicit Neural Representations (2 citations)
and 27 more in the interactive map.
Text-to-image diffusion · 24 papers
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis (92 citations)
- Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts (8 citations)
- Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (4 citations)
- Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization (4 citations)
- Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators (3 citations)
- Prompt-tuning Latent Diffusion Models for Inverse Problems (2 citations)
- The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline (2 citations)
- An Image is Worth Multiple Words: Discovering Object Level Concepts using Multi-Concept Prompt Learning (1 citation)
- ArtWhisperer: A Dataset for Characterizing Human-AI Interactions in Artistic Creations (1 citation)
- Compositional Text-to-Image Generation with Dense Blob Representations (1 citation)
- HyperFields: Towards Zero-Shot Generation of NeRFs from Text (1 citation)
- On Discrete Prompt Optimization for Diffusion Models (1 citation)
and 12 more in the interactive map.
Image restoration · 10 papers
- DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency (4 citations)
- Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge (4 citations)
- Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity (2 citations)
- Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration (2 citations)
- Optimal Eye Surgeon: Finding image priors through sparse generators at initialization (1 citation)
- Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder
- Test-Time Degradation Adaptation for Open-Set Image Restoration
- The Perception-Robustness Tradeoff in Deterministic Image Restoration
- Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach
- DiffFPR: Diffusion Prior for Oversampled Fourier Phase Retrieval
Editing and style transfer · 5 papers
- Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion (1 citation)
- Counterfactual Image Editing
- MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion
- Prompt-guided Precise Audio Editing with Diffusion Models
- Transferable Facial Privacy Protection against Blind Face Restoration via Domain-Consistent Adversarial Obfuscation
GANs · 5 papers
- E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation (1 citation)
- MS$^3$D: A RG Flow-Based Regularization for GAN Training with Limited Data
- SMaRt: Improving GANs with Score Matching Regularity
- Bridging Data Gaps in Diffusion Models with Adversarial Noise-Based Transfer Learning
- Improving Adversarial Energy-Based Model via Diffusion Process
Super-resolution · 4 papers
- See More Details: Efficient Image Super-Resolution by Experts Mining (1 citation)
- Exploring the Low-Pass Filtering Behavior in Image Super-Resolution
- Flexible Residual Binarization for Image Super-Resolution
- MFTN: A Multi-scale Feature Transfer Network Based on IMatchFormer for Hyperspectral Image Super-Resolution