Scaling generative inverse and forward rendering to real-world scenarios is bottlenecked by the limited realism and temporal coherence of existing synthetic datasets. To bridge this persistent domain gap, we introduce a large-scale, dynamic dataset curated from visually complex AAA games. Using a novel dual-screen stitched capture method, we extracted 4M continuous frames (720p/30 FPS) of synchronized RGB and five G-buffer channels across diverse scenes, visual effects, and environments, including adverse weather and motion-blur variants. This dataset uniquely advances bidirectional rendering: enabling robust in-the-wild geometry and material decomposition, and facilitating high-fidelity G-buffer-guided video generation. Furthermore, to evaluate the real-world performance of inverse rendering without ground truth, we propose a novel VLM-based assessment protocol measuring semantic, spatial, and temporal consistency. Experiments demonstrate that inverse renderers fine-tuned on our data achieve superior cross-dataset generalization and controllable generation, while our VLM evaluation strongly correlates with human judgment. Combined with our toolkit, our forward renderer enables users to edit styles of AAA games from G-buffers using text prompts.
@article{arxiv.2604.02329,
title = {Generative World Renderer},
author = {Zheng-Hui Huang and Zhixiang Wang and Jiaming Tan and Ruihan Yu and Yidan Zhang and Bo Zheng and Yu-Lun Liu and Yung-Yu Chuang and Kaipeng Zhang},
journal= {arXiv preprint arXiv:2604.02329},
year = {2026}
}