游戏内任意风格迁移新方法，兼顾速度与画质稳定性。
PQDAST: Depth-Aware Arbitrary Style Transfer for Games via Perceptual Quality-Guided Distillation
- 用感知质量引导的压缩知识蒸馏，降低内存与耗时。
- 训练数据融合深度与时间信息，保留细节与景深。
- 可直接嵌入渲染管线，实现稳定动态风格化效果。
艺术风格迁移旨在生成融合图像内容与艺术作品风格的图像。在游戏领域，多数工作集中在视频帧的后处理，少数近期研究将风格迁移融入游戏管线，但仅支持单一风格。将任意风格迁移集成到游戏引擎面临内存与速度双重挑战。本文提出PQDAST，首个解决该问题的方法。采用感知质量引导的知识蒸馏框架，利用FLIP评估器训练压缩模型，显著降低内存占用与处理时间，同时保持风格化质量。为更好保留深度与细节，在训练中使用含深度与时间信息的合成数据集。所提模型被注入渲染管线，进一步增强时间一致性，避免后处理效果衰减。定量与定性实验表明，本方法在时间一致性上优于现有图像、视频及游戏内方法，风格迁移质量相当。
原文摘要 · Abstract (English)
Artistic style transfer is concerned with the generation of imagery that combines the content of an image with the style of an artwork. In the realm of computer games, most work has focused on post-processing video frames. Some recent work has integrated style transfer into the game pipeline, but it is limited to single styles. Integrating an arbitrary style transfer method into the game pipeline is challenging due to the memory and speed requirements of games. We present PQDAST, the first solution to address this. We use a perceptual quality-guided knowledge distillation framework and train a compressed model using the FLIP evaluator, which substantially reduces both memory usage and processing time with limited impact on stylisation quality. For better preservation of depth and fine details, we utilise a synthetic dataset with depth and temporal considerations during training. The developed model is injected into the rendering pipeline to further enforce temporal stability and avoid diminishing post-process effects. Quantitative and qualitative experiments demonstrate that our approach achieves superior performance in temporal consistency, with comparable style transfer quality, to state-of-the-art image, video and in-game methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。