Reflection Generation for Composite Image Using Diffusion Model

TL;DR

This paper introduces a novel diffusion model-based method for generating realistic reflections in composite images, supported by a new large-scale reflection dataset, setting a new benchmark in the field.

Contribution

It presents a reflection generation approach that incorporates prior reflection information and type-aware design, filling a gap in existing shadow-focused research.

Findings

Generated reflections are physically coherent and visually realistic.

The method establishes a new benchmark for reflection generation.

Constructed the first large-scale object reflection dataset DEROBA.

Abstract

Image composition involves inserting a foreground object into the background while synthesizing environment-consistent effects such as shadows and reflections. Although shadow generation has been extensively studied, reflection generation remains largely underexplored. In this work, we focus on reflection generation. We inject the prior information of reflection placement and reflection appearance into foundation diffusion model. We also divide reflections into two types and adopt type-aware model design. To support training, we construct the first large-scale object reflection dataset DEROBA. Experiments demonstrate that our method generates reflections that are physically coherent and visually realistic, establishing a new benchmark for reflection generation.