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

2025-08-20

AI Summary

Existing methods model forward and inverse rendering as separate multi-step diffusion processes, leading to cycle inconsistency, slow inference, and temporal artifacts in video generation. To address these issues, this paper proposes Dual-One-Step Diffusion—a novel framework that unifies single-step diffusion for jointly learning cycle-consistent forward rendering and intrinsic decomposition. By sharing a latent space and enforcing bidirectional gradient coupling, the two tasks mutually enhance each other, while an explicit cycle-consistency constraint further ensures fidelity. The framework achieves high-quality intrinsic decomposition across both indoor and outdoor scenes and generalizes zero-shot to video decomposition without fine-tuning. Experiments demonstrate state-of-the-art rendering quality, 3–5× faster inference than prevailing multi-step diffusion models, and significantly reduced inter-frame inconsistency in video sequences.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Single-step diffusion for bidirectional rendering consistency
• Cycle consistency between forward and inverse rendering outputs
• Reducing temporal inconsistency in video decomposition transfer

Innovation

• Single-step diffusion models for rendering
• Cycle consistency mechanism for coherence
• Training-free video decomposition transfer