Translations:Diffusion Models Are Real-Time Game Engines/81/zh: Difference between revisions

Latest revision as of 00:29, 9 September 2024

Information about message (contribute)

This message has no documentation. If you know where or how this message is used, you can help other translators by adding documentation to this message.

Message definition (Diffusion Models Are Real-Time Game Engines)

Neural methods for reconstructing 3D representations have made significant advances over the last years. NeRFs (Mildenhall et al., [https://arxiv.org/html/2408.14837v1#bib.bib20 2020]) parameterize radiance fields using a deep neural network that is specifically optimized for a given scene from a set of images taken from various camera poses. Once trained, novel points of view of the scene can be sampled using volume rendering methods. Gaussian Splatting (Kerbl et al., [https://arxiv.org/html/2408.14837v1#bib.bib15 2023]) approaches build on NeRFs but represent scenes using 3D Gaussians and adapted rasterization methods, unlocking faster training and rendering times. While demonstrating impressive reconstruction results and real-time interactivity, these methods are often limited to static scenes.

重建三维表示的神经方法在过去几年中取得了重大进展。NeRFs（Mildenhall 等人，2020）使用深度神经网络对辐射场进行参数化，该网络针对从不同相机姿态拍摄的一组图像的特定场景进行了专门优化。训练完成后，可通过体积渲染方法对场景的新视角进行采样。Gaussian Splatting（Kerbl 等人，2023）方法建立在 NeRFs 的基础上，但使用三维高斯和改进的光栅化方法来表示场景，从而实现更快的训练和渲染速度。尽管这些方法展示了令人印象深刻的重建结果和实时交互性，但通常仅限于静态场景。