RemEdit: Efficient Diffusion Editing with Riemannian Geometry

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Adhikarla, Eashan, Davison, Brian D.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912848535355392
author Adhikarla, Eashan
Davison, Brian D.
author_facet Adhikarla, Eashan
Davison, Brian D.
contents Controllable image generation is fundamental to the success of modern generative AI, yet it faces a critical trade-off between semantic fidelity and inference speed. The RemEdit diffusion-based framework addresses this trade-off with two synergistic innovations. First, for editing fidelity, we navigate the latent space as a Riemannian manifold. A mamba-based module efficiently learns the manifold's structure, enabling direct and accurate geodesic path computation for smooth semantic edits. This control is further refined by a dual-SLERP blending technique and a goal-aware prompt enrichment pass from a Vision-Language Model. Second, for additional acceleration, we introduce a novel task-specific attention pruning mechanism. A lightweight pruning head learns to retain tokens essential to the edit, enabling effective optimization without the semantic degradation common in content-agnostic approaches. RemEdit surpasses prior state-of-the-art editing frameworks while maintaining real-time performance under 50% pruning. Consequently, RemEdit establishes a new benchmark for practical and powerful image editing. Source code: https://www.github.com/eashanadhikarla/RemEdit.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17927
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RemEdit: Efficient Diffusion Editing with Riemannian Geometry
Adhikarla, Eashan
Davison, Brian D.
Computer Vision and Pattern Recognition
Multimedia
Controllable image generation is fundamental to the success of modern generative AI, yet it faces a critical trade-off between semantic fidelity and inference speed. The RemEdit diffusion-based framework addresses this trade-off with two synergistic innovations. First, for editing fidelity, we navigate the latent space as a Riemannian manifold. A mamba-based module efficiently learns the manifold's structure, enabling direct and accurate geodesic path computation for smooth semantic edits. This control is further refined by a dual-SLERP blending technique and a goal-aware prompt enrichment pass from a Vision-Language Model. Second, for additional acceleration, we introduce a novel task-specific attention pruning mechanism. A lightweight pruning head learns to retain tokens essential to the edit, enabling effective optimization without the semantic degradation common in content-agnostic approaches. RemEdit surpasses prior state-of-the-art editing frameworks while maintaining real-time performance under 50% pruning. Consequently, RemEdit establishes a new benchmark for practical and powerful image editing. Source code: https://www.github.com/eashanadhikarla/RemEdit.
title RemEdit: Efficient Diffusion Editing with Riemannian Geometry
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2601.17927