FrameDiffuser: G-Buffer-Conditioned Diffusion for Neural Forward Frame Rendering

TL;DR

FrameDiffuser is an autoregressive neural rendering method that produces temporally consistent, photorealistic frames conditioned on G-buffer data and previous outputs, suitable for interactive applications.

Contribution

It introduces a novel G-buffer-conditioned diffusion framework with dual-conditioning architecture and environment-specific training for real-time, consistent neural rendering.

Findings

Achieves stable, high-quality rendering over hundreds of frames

Outperforms generalized models in photorealism and lighting accuracy

Operates efficiently for interactive applications

Abstract

Neural rendering for interactive applications requires translating geometric and material properties (G-buffer) to photorealistic images with realistic lighting on a frame-by-frame basis. While recent diffusion-based approaches show promise for G-buffer-conditioned image synthesis, they face critical limitations: single-image models like RGBX generate frames independently without temporal consistency, while video models like DiffusionRenderer are too computationally expensive for most consumer gaming sets ups and require complete sequences upfront, making them unsuitable for interactive applications where future frames depend on user input. We introduce FrameDiffuser, an autoregressive neural rendering framework that generates temporally consistent, photorealistic frames by conditioning on G-buffer data and the models own previous output. After an initial frame, FrameDiffuser operates purely on incoming G-buffer data, comprising geometry, materials, and surface properties, while using its previously generated frame for temporal guidance, maintaining stable, temporal consistent generation over hundreds to thousands of frames. Our dual-conditioning architecture combines ControlNet for structural guidance with ControlLoRA for temporal coherence. A three-stage training strategy enables stable autoregressive generation. We specialize our model to individual environments, prioritizing consistency and inference speed over broad generalization, demonstrating that environment-specific training achieves superior photorealistic quality with accurate lighting, shadows, and reflections compared to generalized approaches.