REVIEW 8 cited by
The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We present a unified probabilistic formulation for diffusion-based image editing, where a latent variable is edited in a task-specific manner and generally deviates from the corresponding marginal distribution induced by the original stochastic or ordinary differential equation (SDE or ODE). Instead, it defines a corresponding SDE or ODE for editing. In the formulation, we prove that the Kullback-Leibler divergence between the marginal distributions of the two SDEs gradually decreases while that for the ODEs remains as the time approaches zero, which shows the promise of SDE in image editing. Inspired by it, we provide the SDE counterparts for widely used ODE baselines in various tasks including inpainting and image-to-image translation, where SDE shows a consistent and substantial improvement. Moreover, we propose SDE-Drag -- a simple yet effective method built upon the SDE formulation for point-based content dragging. We build a challenging benchmark (termed DragBench) with open-set natural, art, and AI-generated images for evaluation. A user study on DragBench indicates that SDE-Drag significantly outperforms our ODE baseline, existing diffusion-based methods, and the renowned DragGAN. Our results demonstrate the superiority and versatility of SDE in image editing and push the boundary of diffusion-based editing methods.
Forward citations
Cited by 8 Pith papers
-
FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors
Interactive image editing can be cast as image-to-video generation: initializing from Stable Video Diffusion plus a new matching attention mechanism yields high-quality sketch, drag, and coarse-edit results with far l...
-
Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping
Drag-based editing becomes pixel-space bidirectional warping plus inpainting, giving real-time previews and 0.3s final edits at 512x512.
-
Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting
DYG edits 3D Gaussian scenes by dragging masked regions to target points, using a triplane positional scaffold and a drag-based latent diffusion score-distillation loss.
-
DragScene: Interactive 3D Scene Editing with Single-view Drag Instructions
DragScene propagates a single-view drag edit across multiple views by reconstructing a coarse point cloud with the edit's latent features, then reconstructing the edited 3D scene.
-
ARAP-GS: Drag-driven As-Rigid-As-Possible 3D Gaussian Splatting Editing with Diffusion Prior
A drag-driven 3DGS editing method that applies as-rigid-as-possible deformation directly to Gaussian centers and then fine-tunes appearance with a diffusion super-resolution prior.
-
MagicQuill: An Intelligent Interactive Image Editing System
MagicQuill combines brush-based edge and color control with an MLLM that guesses user intent, enabling fast interactive image edits without typing prompts.
-
SeedEdit 3.0: Fast and High-Quality Generative Image Editing
SeedEdit 3.0 reports a 56.1% usability rate on internal real-image editing tests, beating SeedEdit 1.6, GPT-4o, and Gemini 2.0, with 8x faster inference after distillation and quantization.
-
Efficient Diffusion Models: A Survey
The paper organizes research on efficient diffusion models into a taxonomy spanning algorithms, systems, and frameworks, and provides a curated reference list.
Discussion (0). Continue with ORCID to comment.