mlsanityData to 7 Oct 2026

EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing

arXiv 2503.10270 ↗First posted 13 Mar 2025cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

Inversion-based image editing is rapidly gaining momentum while suffering from significant computation overhead, hindering its application in real-time interactive scenarios. In this paper, we rethink that the redundancy in inversion-based image editing exists in both the spatial and temporal dimensions, such as the unnecessary computation in unedited regions and the redundancy in the inversion progress. To tackle these challenges, we propose a practical framework, named EEdit, to achieve efficient image editing. Specifically, we introduce three techniques to solve them one by one. For spatial redundancy, spatial locality caching is introduced to compute the edited region and its neighboring regions while skipping the unedited regions, and token indexing preprocessing is designed to further accelerate the caching. For temporal redundancy, inversion step skipping is proposed to reuse the latent for efficient editing. Our experiments demonstrate an average of 2.46 × acceleration without performance drop in a wide range of editing tasks including prompt-guided image editing, dragging and image composition. Our codes are available at https://github.com/yuriYanZeXuan/EEdit

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 71 of its 101 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

71 of 101 references.

References · 71

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2022Scalable Diffusion Models with Transformerscited by 5,931
  5. 2022Flow Matching for Generative Modelingcited by 5,426
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  7. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  8. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  9. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  10. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  11. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  12. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,168
38 more
  1. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  2. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 722
  3. 2023DeepCache: Accelerating Diffusion Models for Freecited by 346
  4. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 331
  5. 2023Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videoscited by 312
  6. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
  7. 2023DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editingcited by 293
  8. 2023Token Merging for Fast Stable Diffusioncited by 220
  9. 2024FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Modelscited by 214
  10. 2024Taming Rectified Flow for Inversion and Editingcited by 200
  11. 2023DreamVideo: Composing Your Dream Videos with Customized Subject and Motioncited by 186
  12. 2023TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Compositioncited by 182
  13. 2024Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animationcited by 172
  14. 2024Semantic Image Inversion and Editing using Rectified Stochastic Differential Equationscited by 162
  15. 2024Accelerating Diffusion Transformers with Token-wise Feature Cachingcited by 143
  16. 2023SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generationcited by 142
  17. 2024Learning-to-Cache: Accelerating Diffusion Transformer via Layer Cachingcited by 138
  18. 2024FORA: Fast-Forward Caching in Diffusion Transformer Accelerationcited by 127
  19. 2025EasyControl: Adding Efficient and Flexible Control for Diffusion Transformercited by 118
  20. 2023Inversion-Free Image Editing with Natural Languagecited by 106
  21. 2024DiT4Edit: Diffusion Transformer for Image Editingcited by 100
  22. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 87
  23. 2023Effective Real Image Editing with Accelerated Iterative Diffusion Inversioncited by 79
  24. 2023MagicStick: Controllable Video Editing via Control Handle Transformationscited by 62
  25. 2025Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Taskscited by 62
  26. 2023The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editingcited by 61
  27. 2024COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editingcited by 59
  28. 2024Faster Diffusion via Temporal Attention Decompositioncited by 54
  29. 2024Follow-Your-Click: Open-domain Regional Image Animation via Short Promptscited by 52
  30. 2025VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editingcited by 50
  31. 2025KV-Edit: Training-Free Image Editing for Precise Background Preservationcited by 47
  32. 2022DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonizationcited by 46
  33. 2024MultiBooth: Towards Generating All Your Concepts in an Image from Textcited by 45
  34. 2024Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Modelcited by 44
  35. 2024Image Watermarks are Removable Using Controllable Regeneration from Clean Noisecited by 43
  36. 2025LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformercited by 43
  37. 2025MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generationcited by 43
  38. 2024Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generationcited by 42

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 27; 2026: 18.

45 papers.

Sort:

By area:

  1. 2025Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Modelscited by 92
  2. 2025Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuningcited by 81
  3. 2025Follow-Your-Creation: Empowering 4D Creation through Video Inpaintingcited by 61
  4. 2025Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animationcited by 41
  5. 2025JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agentcited by 39
  6. 2025Does FLUX Already Know How to Perform Physically Plausible Image Composition?cited by 30
  7. 2025DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editingcited by 29
  8. 2025Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Controlcited by 27
  9. 2025ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichmentcited by 27
  10. 2025Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Modelscited by 24
  11. 2025DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editingcited by 22
  12. 2025A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generationcited by 14
33 more
  1. 2025SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skippingcited by 11
  2. 2025Adams Bashforth Moulton Solver for Inversion and Editing in Rectified Flowcited by 10
  3. 2025Follow-Your-Instruction: A Comprehensive MLLM Agent for World Data Synthesiscited by 10
  4. 2026VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformerscited by 8
  5. 2025SpotEdit: Selective Region Editing in Diffusion Transformerscited by 7
  6. 2026LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generationcited by 6
  7. 2025EA-ViT: Efficient Adaptation for Elastic Vision Transformercited by 5
  8. 2025Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformercited by 5
  9. 2025The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignmentcited by 5
  10. 2026Embedding-perturbed Exploration Preference Optimization for Flow Modelscited by 5
  11. 2026RebuttalAgent: Strategic Persuasion in Academic Rebuttal via Theory of Mindcited by 4
  12. 2026DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Cachingcited by 4
  13. 2026GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflowscited by 4
  14. 2025MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion Transformercited by 3
  15. 2026EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generationcited by 2
  16. 2025Unified Long Video Inpainting and Outpainting via Overlapping High-Order Co-Denoisingcited by 1
  17. 2025DirectDrag: High-Fidelity, Mask-Free, Prompt-Free Drag-based Image Editing via Readout-Guided Feature Alignmentcited by 1
  18. 2025RealDrag: The First Dragging Benchmark with Real Target Imagecited by 1
  19. 2025Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breakingcited by 1
  20. 2026Unsafe2Safe: Controllable Image Anonymization for Downstream Utilitycited by 1
  21. 2026FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Cachingcited by 1
  22. 2026SWEET: Sparse World Modeling with Image Editing for Embodied Task Executioncited by 1
  23. 2026Bridging the Manifold Gap: Riemannian Residual Line Search for One-Step Image Editingcited by 1
  24. 2026CameraEditor: Camera-Controlled Image Editing via Video-Prior Sequential Modelingcited by 1
  25. 2025MotionDiff: Training-free Zero-shot Interactive Motion Editing via Flow-assisted Multi-view Diffusioncited by 0
  26. 2025FADE: Adversarial Concept Erasure in Flow Modelscited by 0
  27. 2025Understanding the Implicit User Intention via Reasoning with Large Language Model for Image Editingcited by 0
  28. 2026Uni-Animator: Towards Unified Visual Colorizationcited by 0
  29. 2026GPO-V: Jailbreak Diffusion Vision Language Model by Global Probability Optimizationcited by 0
  30. 2026LimeCross: Context-Conditioned Layered Image Editing with Structural Consistencycited by 0
  31. 2026In-context Region-based Drag: Drag Any Region to Any Shapecited by 0
  32. 2026SR-Edit: Region-Aware Image Editing via Self-Refinementcited by 0
  33. 2026GenPuzzle: Benchmarking Visual Reasoning in Image Generation Modelscited by 0