SAIL: Self-supervised Albedo Estimation from Real Images with a Latent Diffusion Model

TL;DR

SAIL introduces a self-supervised method leveraging latent diffusion models to estimate stable, albedo-like representations from single real-world images, overcoming data scarcity and generalizing across scenes.

Contribution

The paper presents a novel intrinsic image decomposition approach in the latent space using diffusion models, enabling albedo estimation without labeled data.

Findings

Produces consistent albedo maps under different lighting conditions

Generalizes well to multiple real-world scenes

Operates effectively with only unlabeled multi-illumination data

Abstract

Intrinsic image decomposition aims at separating an image into its underlying albedo and shading components, isolating the base color from lighting effects to enable downstream applications such as virtual relighting and scene editing. Despite the rise and success of learning-based approaches, intrinsic image decomposition from real-world images remains a significant challenging task due to the scarcity of labeled ground-truth data. Most existing solutions rely on synthetic data as supervised setups, limiting their ability to generalize to real-world scenes. Self-supervised methods, on the other hand, often produce albedo maps that contain reflections and lack consistency under different lighting conditions. To address this, we propose SAIL, an approach designed to estimate albedo-like representations from single-view real-world images. We repurpose the prior knowledge of a latent diffusion model for unconditioned scene relighting as a surrogate objective for albedo estimation. To extract the albedo, we introduce a novel intrinsic image decomposition fully formulated in the latent space. To guide the training of our latent diffusion model, we introduce regularization terms that constrain both the lighting-dependent and independent components of our latent image decomposition. SAIL predicts stable albedo under varying lighting conditions and generalizes to multiple scenes, using only unlabeled multi-illumination data available online.