Copertina

DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Desong, Ye, Mang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models
di: Jiao, Guanlong, et al.
Pubblicazione: (2025)

InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow
di: Gong, Yiming, et al.
Pubblicazione: (2025)

Optimal Transport for Rectified Flow Image Editing: Unifying Inversion-Based and Direct Methods
di: Lupascu, Marian, et al.
Pubblicazione: (2025)

ChordEdit: One-Step Low-Energy Transport for Image Editing
di: Lu, Liangsi, et al.
Pubblicazione: (2026)

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models
di: Kulikov, Vladimir, et al.
Pubblicazione: (2024)

SNR-Edit: Structure-Aware Noise Rectification for Inversion-Free Flow-Based Editing
di: Jiang, Lifan, et al.
Pubblicazione: (2026)

AdaEdit: Adaptive Temporal and Channel Modulation for Flow-Based Image Editing
di: Li, Guandong, et al.
Pubblicazione: (2026)

SteerFlow: Steering Rectified Flows for Faithful Inversion-Based Image Editing
di: Dao, Thinh, et al.
Pubblicazione: (2026)

TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models
di: Deutch, Gilad, et al.
Pubblicazione: (2024)

Step1X-Edit: A Practical Framework for General Image Editing
di: Liu, Shiyu, et al.
Pubblicazione: (2025)

Pose-Star: Anatomy-Aware Editing for Open-World Fashion Images
di: Dong, Yuran, et al.
Pubblicazione: (2025)

DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing
di: Jia, Yueru, et al.
Pubblicazione: (2024)

ImgEdit: A Unified Image Editing Dataset and Benchmark
di: Ye, Yang, et al.
Pubblicazione: (2025)

ProEdit: Inversion-based Editing From Prompts Done Right
di: Ouyang, Zhi, et al.
Pubblicazione: (2025)

FIA-Edit: Frequency-Interactive Attention for Efficient and High-Fidelity Inversion-Free Text-Guided Image Editing
di: Yang, Kaixiang, et al.
Pubblicazione: (2025)

SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing
di: Yoon, Sung-Hoon, et al.
Pubblicazione: (2025)

FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing
di: Deng, Yingying, et al.
Pubblicazione: (2024)

MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching
di: Huang, Jiahui, et al.
Pubblicazione: (2026)

SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusion
di: Nguyen, Trong-Tung, et al.
Pubblicazione: (2024)

CogniEdit: Dense Gradient Flow Optimization for Fine-Grained Image Editing
di: Li, Yan, et al.
Pubblicazione: (2025)

Group Editing: Edit Multiple Images in One Go
di: Ma, Yue, et al.
Pubblicazione: (2026)

Taming Rectified Flow for Inversion and Editing
di: Wang, Jiangshan, et al.
Pubblicazione: (2024)

SimInversion: A Simple Framework for Inversion-Based Text-to-Image Editing
di: Qian, Qi, et al.
Pubblicazione: (2024)

TweezeEdit: Consistent and Efficient Image Editing with Path Regularization
di: Mao, Jianda, et al.
Pubblicazione: (2025)

EditCLIP: Representation Learning for Image Editing
di: Wang, Qian, et al.
Pubblicazione: (2025)

Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning
di: He, Qingdong, et al.
Pubblicazione: (2025)

ReEdit: Multimodal Exemplar-Based Image Editing with Diffusion Models
di: Srivastava, Ashutosh, et al.
Pubblicazione: (2024)

FREE-Edit: Using Editing-aware Injection in Rectified Flow Models for Zero-shot Image-Driven Video Editing
di: Li, Maomao, et al.
Pubblicazione: (2026)

Lego-Edit: A General Image Editing Framework with Model-Level Bricks and MLLM Builder
di: Jia, Qifei, et al.
Pubblicazione: (2025)

FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing
di: Kim, Jeongsol, et al.
Pubblicazione: (2025)

Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling
di: Bai, Xuehai, et al.
Pubblicazione: (2026)

Object-aware Inversion and Reassembly for Image Editing
di: Yang, Zhen, et al.
Pubblicazione: (2023)

MDE-Edit: Masked Dual-Editing for Multi-Object Image Editing via Diffusion Models
di: Zhu, Hongyang, et al.
Pubblicazione: (2025)

FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing
di: Chen, Ze, et al.
Pubblicazione: (2026)

SeedEdit: Align Image Re-Generation to Image Editing
di: Shi, Yichun, et al.
Pubblicazione: (2024)

PhysEdit: Physically-Consistent Region-Aware Image Editing via Adaptive Spatio-Temporal Reasoning
di: Li, Guandong, et al.
Pubblicazione: (2026)

Rethinking Where to Edit: Task-Aware Localization for Instruction-Based Image Editing
di: He, Jingxuan, et al.
Pubblicazione: (2026)

Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing
di: Yeh, Chun-Hsiao, et al.
Pubblicazione: (2025)

TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing
di: Chen, Sherry X., et al.
Pubblicazione: (2024)

DiT4Edit: Diffusion Transformer for Image Editing
di: Feng, Kunyu, et al.
Pubblicazione: (2024)