Neural Gaffer: Relighting Any Object via Diffusion

TL;DR

Neural Gaffer is a diffusion-based model that relights any object from a single image under new lighting conditions without scene decomposition, demonstrating high-quality results and broad applicability.

Contribution

It introduces a novel end-to-end 2D relighting diffusion model that generalizes to any object and lighting condition without explicit scene decomposition.

Findings

Achieves accurate relighting on synthetic and real images.

Generalizes well to diverse objects and environments.

Enables downstream tasks like text-based relighting and object insertion.

Abstract

Single-image relighting is a challenging task that involves reasoning about the complex interplay between geometry, materials, and lighting. Many prior methods either support only specific categories of images, such as portraits, or require special capture conditions, like using a flashlight. Alternatively, some methods explicitly decompose a scene into intrinsic components, such as normals and BRDFs, which can be inaccurate or under-expressive. In this work, we propose a novel end-to-end 2D relighting diffusion model, called Neural Gaffer, that takes a single image of any object and can synthesize an accurate, high-quality relit image under any novel environmental lighting condition, simply by conditioning an image generator on a target environment map, without an explicit scene decomposition. Our method builds on a pre-trained diffusion model, and fine-tunes it on a synthetic relighting dataset, revealing and harnessing the inherent understanding of lighting present in the diffusion model. We evaluate our model on both synthetic and in-the-wild Internet imagery and demonstrate its advantages in terms of generalization and accuracy. Moreover, by combining with other generative methods, our model enables many downstream 2D tasks, such as text-based relighting and object insertion. Our model can also operate as a strong relighting prior for 3D tasks, such as relighting a radiance field.