ECCV 2026 accepted papers on Image generation
396 of the 2,834 papers accepted at ECCV 2026 (14.0%) are on Image generation, compared with 15.9% at ECCV 2024. They fall into 6 topics.
See ECCV 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Text-to-image diffusion · 107 papers
- TIIF-Bench: How Does Your T2I Model Follow Your Instructions? (69 citations)
- Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility (15 citations)
- RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards (14 citations)
- SAEdit: Token-Level Control for Continuous Image Editing via Sparse Autoencoder (13 citations)
- RubricRL: Simple Generalizable Rewards for Text-to-Image Generation (9 citations)
- DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing (8 citations)
- OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure (8 citations)
- CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation (7 citations)
- Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing (7 citations)
- Learn Once, Edit Anywhere: Visual Direction Transfer for Diffusion Models (7 citations)
- Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning (7 citations)
- Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models (6 citations)
and 95 more in the interactive map.
Fast diffusion sampling · 82 papers
- ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration (19 citations)
- Continuous Speculative Decoding for Autoregressive Image Generation (18 citations)
- DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models (16 citations)
- SD3.5-Flash: Distribution-Guided Distillation of Generative Flows (16 citations)
- One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies (13 citations)
- Towards Consistent and Efficient Dataset Distillation via Diffusion-Driven Selection (10 citations)
- MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding (9 citations)
- ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion (7 citations)
- SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization (7 citations)
- Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching (6 citations)
- Continuous Adversarial Flow Models (5 citations)
- Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning (5 citations)
and 70 more in the interactive map.
Autoregressive and latent generation · 72 papers
- Towards Scalable Pre-training of Visual Tokenizers for Generation (27 citations)
- The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding (19 citations)
- Representation Alignment for Just Image Transformers is not Easier than You Think (18 citations)
- Beyond Artifacts: Real-Centric Envelope Modeling for Reliable AI-Generated Image Detection (17 citations)
- Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders (15 citations)
- ELT: Elastic Looped Transformers for Visual Generation (12 citations)
- Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples (9 citations)
- PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion (7 citations)
- DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space (6 citations)
- Vision Bridge Transformer at Scale (6 citations)
- Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens (5 citations)
- AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation (4 citations)
and 60 more in the interactive map.
Editing and style transfer · 55 papers
- PPTArena: A Benchmark for PowerPoint Editing (15 citations)
- WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing (8 citations)
- Target-aware Image Editing via Cycle-consistent Constraints (5 citations)
- Spanning the Visual Analogy Space with a Weight Basis of LoRAs (4 citations)
- FitControler: Toward Fit-Aware Virtual Try-On (3 citations)
- EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal (2 citations)
- TanGO: Training-Free 3D Editing via Tangent-Space Guidance and Optimization (2 citations)
- VTEdit-Bench: A Comprehensive Benchmark for Multi-Reference Image Editing Models in Virtual Try-On (2 citations)
- FED-Bench: A Cross-Granular Benchmark for Disentangled Evaluation of Facial Expression Editing (1 citation)
- FineEdit: Fine-Grained Image Edit with Bounding Box Guidance (1 citation)
- MTVDiff: Multimodal Conditional Latent Diffusion for Enhanced Thermal-to-Visible Face Translation (1 citation)
- Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset (1 citation)
and 43 more in the interactive map.
Image restoration · 44 papers
- Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging (9 citations)
- Filterless Snapshot Hyperspectral Imaging using Guided Patch Diffusion (4 citations)
- FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal (2 citations)
- HNDiff: Haze-Noise Diffusion for Image Dehazing (1 citation)
- MambaRaw: Selective State Space Modeling for Efficient 4K RAW Image Reconstruction (1 citation)
- SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restoration (1 citation)
- Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization (1 citation)
- VSDiffusion: Taming Ill-Posed Shadow Generation via Visibility-Constrained Diffusion (1 citation)
- Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization
- BWAFDA: Block-wise Weighted Attention Fusion with Detail-aware for No-Reference Image Quality Assessment
- CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion
- Controllable Generative Reference for Stereo Image Compression via Reliability-Aware Gating
and 32 more in the interactive map.
Super-resolution · 36 papers
- FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI (6 citations)
- Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution (3 citations)
- OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution (2 citations)
- Resolution-Agnostic Neural Operators for Multi-Rate Sparse-View CT (2 citations)
- RefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution (1 citation)
- TEASR: Training-Efficient Any-Step Diffusion Transformer for Real-World Image Super-Resolution (1 citation)
- AdaBridge-SR: Adaptive Bridge Matching for Real-World Image Super-Resolution
- Adversarial Score Distillation for Stable One-Step Diffusion in Real-World Image Super-Resolution
- Allo{SR}2: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows
- CARA: Collision-Aware Resolution Adaptation for Multiresolution Hash Encoding Based Image Fitting
- CUST : Clustered Unit-level Similarity Transformer for Lightweight Image Super-Resolution
- DRIFT: Difficulty-aware Rectified Flows for Through-plane MRI Super-Resolution
and 24 more in the interactive map.
