Inversion-by-Inversion: Exemplar-based Sketch-to-Photo Synthesis via Stochastic Differential Equations without Training

TL;DR

This paper introduces a training-free, two-stage inversion method for exemplar-based sketch-to-photo synthesis, effectively controlling shape, color, and texture without training diffusion models.

Contribution

It presents a novel, training-free inversion pipeline that enhances shape and appearance control in sketch-to-photo synthesis using energy functions.

Findings

Effective shape control via shape-energy guided inversion

Accurate color and texture synthesis with appearance-energy function

Training-free approach adaptable to various exemplars

Abstract

Exemplar-based sketch-to-photo synthesis allows users to generate photo-realistic images based on sketches. Recently, diffusion-based methods have achieved impressive performance on image generation tasks, enabling highly-flexible control through text-driven generation or energy functions. However, generating photo-realistic images with color and texture from sketch images remains challenging for diffusion models. Sketches typically consist of only a few strokes, with most regions left blank, making it difficult for diffusion-based methods to produce photo-realistic images. In this work, we propose a two-stage method named ``Inversion-by-Inversion" for exemplar-based sketch-to-photo synthesis. This approach includes shape-enhancing inversion and full-control inversion. During the shape-enhancing inversion process, an uncolored photo is generated with the guidance of a shape-energy function. This step is essential to ensure control over the shape of the generated photo. In the full-control inversion process, we propose an appearance-energy function to control the color and texture of the final generated photo.Importantly, our Inversion-by-Inversion pipeline is training-free and can accept different types of exemplars for color and texture control. We conducted extensive experiments to evaluate our proposed method, and the results demonstrate its effectiveness. The code and project can be found at https://ximinng.github.io/inversion-by-inversion-project/.