Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering

TL;DR

Ouroboros introduces a pair of single-step diffusion models for cycle-consistent forward and inverse rendering, achieving state-of-the-art results with faster inference and applicability to video decomposition.

Contribution

The paper proposes a novel framework with two mutual reinforcement diffusion models that ensure cycle consistency and extend to video without additional training.

Findings

State-of-the-art performance across diverse scenes

Substantially faster inference speed

Effective transfer to video decomposition without training

Abstract

While multi-step diffusion models have advanced both forward and inverse rendering, existing approaches often treat these problems independently, leading to cycle inconsistency and slow inference speed. In this work, we present Ouroboros, a framework composed of two single-step diffusion models that handle forward and inverse rendering with mutual reinforcement. Our approach extends intrinsic decomposition to both indoor and outdoor scenes and introduces a cycle consistency mechanism that ensures coherence between forward and inverse rendering outputs. Experimental results demonstrate state-of-the-art performance across diverse scenes while achieving substantially faster inference speed compared to other diffusion-based methods. We also demonstrate that Ouroboros can transfer to video decomposition in a training-free manner, reducing temporal inconsistency in video sequences while maintaining high-quality per-frame inverse rendering.