DNF-Intrinsic: Deterministic Noise-Free Diffusion for Indoor Inverse Rendering

TL;DR

DNF-Intrinsic introduces a robust inverse rendering method that directly predicts intrinsic properties from source images using a diffusion model, outperforming existing approaches on synthetic and real data.

Contribution

It proposes a novel approach that takes source images as input for intrinsic prediction, improving robustness and accuracy over noise-based methods.

Findings

Outperforms state-of-the-art methods on synthetic datasets.

Achieves superior results on real-world datasets.

Provides physically faithful intrinsic predictions.

Abstract

Recent methods have shown that pre-trained diffusion models can be fine-tuned to enable generative inverse rendering by learning image-conditioned noise-to-intrinsic mapping. Despite their remarkable progress, they struggle to robustly produce high-quality results as the noise-to-intrinsic paradigm essentially utilizes noisy images with deteriorated structure and appearance for intrinsic prediction, while it is common knowledge that structure and appearance information in an image are crucial for inverse rendering. To address this issue, we present DNF-Intrinsic, a robust yet efficient inverse rendering approach fine-tuned from a pre-trained diffusion model, where we propose to take the source image rather than Gaussian noise as input to directly predict deterministic intrinsic properties via flow matching. Moreover, we design a generative renderer to constrain that the predicted intrinsic properties are physically faithful to the source image. Experiments on both synthetic and real-world datasets show that our method clearly outperforms existing state-of-the-art methods.