NeurIPS 2024 accepted papers on Image generation
333 of the 4,560 papers accepted at NeurIPS 2024 (7.3%) are on Image generation, compared with 7.1% at NeurIPS 2023. They fall into 7 topics.
See NeurIPS 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 · 107 papers
- Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion (47 citations)
- Improved Distribution Matching Distillation for Fast Image Synthesis (43 citations)
- Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion (38 citations)
- Guiding a Diffusion Model with a Bad Version of Itself (22 citations)
- Understanding Hallucinations in Diffusion Models through Mode Interpolation (20 citations)
- Rethinking the Diffusion Models for Missing Data Imputation: A Gradient Flow Perspective (17 citations)
- Simplified and Generalized Masked Diffusion for Discrete Data (15 citations)
- Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction (14 citations)
- SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout (13 citations)
- DiffuserLite: Towards Real-time Diffusion Planning (11 citations)
- One-Step Diffusion Distillation through Score Implicit Matching (11 citations)
- Phased Consistency Models (11 citations)
and 95 more in the interactive map.
Autoregressive and latent generation · 74 papers
- Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction (111 citations)
- Autoregressive Image Generation without Vector Quantization (38 citations)
- HEST-1k: A Dataset For Spatial Transcriptomics and Histology Image Analysis (35 citations)
- Invisible Image Watermarks Are Provably Removable Using Generative AI (35 citations)
- Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer (31 citations)
- Simple and Effective Masked Diffusion Language Models (28 citations)
- ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization (23 citations)
- An Image is Worth 32 Tokens for Reconstruction and Generation (18 citations)
- Attack-Resilient Image Watermarking Using Stable Diffusion (15 citations)
- Neural Gaffer: Relighting Any Object via Diffusion (12 citations)
- DiffGS: Functional Gaussian Splatting Diffusion (11 citations)
- GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks (11 citations)
and 62 more in the interactive map.
Text-to-image diffusion · 72 papers
- Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models (19 citations)
- CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching (16 citations)
- PuLID: Pure and Lightning ID Customization via Contrastive Alignment (14 citations)
- GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing (11 citations)
- ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization (11 citations)
- Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance (10 citations)
- Multimodal Large Language Models Make Text-to-Image Generative Models Align Better (8 citations)
- Aligning Diffusion Models by Optimizing Human Utility (6 citations)
- GuardT2I: Defending Text-to-Image Models from Adversarial Prompts (6 citations)
- Images that Sound: Composing Images and Sounds on a Single Canvas (6 citations)
- Slight Corruption in Pre-training Data Makes Better Diffusion Models (6 citations)
- Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models (5 citations)
and 60 more in the interactive map.
Image restoration · 37 papers
- PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging (18 citations)
- Blind Image Restoration via Fast Diffusion Inversion (17 citations)
- Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image Fusion (17 citations)
- DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation (16 citations)
- Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model (15 citations)
- Conditional Controllable Image Fusion (11 citations)
- SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening (11 citations)
- Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention (10 citations)
- Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models (10 citations)
- Image Reconstruction Via Autoencoding Sequential Deep Image Prior (9 citations)
- RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models (7 citations)
- Diffusion Priors for Variational Likelihood Estimation and Image Denoising (4 citations)
and 25 more in the interactive map.
Editing and style transfer · 35 papers
- IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation (51 citations)
- Zero-shot Image Editing with Reference Imitation (17 citations)
- DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion (13 citations)
- IF-Font: Ideographic Description Sequence-Following Font Generation (7 citations)
- Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing (7 citations)
- TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control (6 citations)
- Benchmarking Counterfactual Image Generation (5 citations)
- SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models (5 citations)
- CLIPAway: Harmonizing focused embeddings for removing objects via diffusion models (4 citations)
- Exploring Low-Dimensional Subspace in Diffusion Models for Controllable Image Editing (4 citations)
- HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion (4 citations)
- HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach (4 citations)
and 23 more in the interactive map.
Super-resolution · 7 papers
- One-Step Effective Diffusion Network for Real-World Image Super-Resolution (62 citations)
- Binarized Diffusion Model for Image Super-Resolution (12 citations)
- SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution (3 citations)
- Precipitation Downscaling with Spatiotemporal Video Diffusion (2 citations)
- Rethinking Imbalance in Image Super-Resolution for Efficient Inference (2 citations)
- Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs (2 citations)
- UPS: Unified Projection Sharing for Lightweight Single-Image Super-resolution and Beyond