arXiv Computer Vision
Bridging the Manifold Gap: Riemannian Residual Line Search for One-Step Image Editing
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Jul 1
Stable and Near-Reversible Diffusion ODE Solvers for Image Editing
arXiv:2605. 16399v2 Announce Type: replace-cross Abstract: The inversion of diffusion models plays a central role in image editing.
Hugging Face Trending Papers
Jul 23
SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion
Rectified-flow-based diffusion transformers, particularly FLUX, have demonstrated outstanding performance in high-quality image generation. However, achieving fast and accurate inversion--transforming images back to latent noise for faithful reconstruction and editing--remains a challenging bottleneck due to the discretization errors of linear solvers.
arXiv AI
Aug 11
SNR-Edit: Structure-Aware Noise Rectification for Inversion-Free Flow-Based Editing
arXiv:2601. 19180v2 Announce Type: replace-cross Abstract: Inversion-free image editing using flow-based generative models challenges the prevailing inversion-based pipelines.
arXiv Machine Learning
Jun 29
StableMotion: One-Step Motion Estimation with Diffusion Prior
arXiv:2505. 06668v2 Announce Type: replace-cross Abstract: We present StableMotion, a novel framework that leverages geometric and content priors from pretrained large-scale image diffusion models for motion estimation in single-image rectification tasks such as Stitched Image Rectangling (SIR) and Rolling Shutter Correction (RSC).
arXiv Machine Learning
Jun 2
Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models
arXiv:2605. 31162v1 Announce Type: cross Abstract: Unconditional diffusion models offer powerful generative priors, yet steering them toward aesthetically enhanced outputs remains largely unexplored.
arXiv Computer Vision
Sep 21
Geometry-Aware Diffusion Guidance via Curvature-Adaptive Tubular Correction
The paper introduces Curvature-Adaptive Tubular Correction (CAT), a training‑free plugin that refines diffusion guidance by decomposing the guidance gradient into normal and tangent components and regulating them within a noise‑dependent geometric budget. CAT charges normal displacement at first order and tangent displacement according to directional curvature, solving a one‑dimensional dual equation for optimal magnitudes and using Armijo backtracking to calibrate the step size. Experiments on seven inverse problems with FFHQ and ImageNet demonstrate that CAT consistently improves pixel‑ and latent‑space samplers, enhances perceptual metrics, and achieves the lowest FID across classifier‑free guidance scales while maintaining stable saturation and contrast.