PixelSynth：从单个图像生成3D一致性体验
PixelSynth: Generating a 3D-Consistent Experience from a Single Image
摘要：
微分渲染和3D推理的最新进展已经在从单个图像合成新视图方面取得了令人兴奋的结果。尽管有现实的结果，方法仅限于相对较小的视图变化。为了合成沉浸式场景，模型还必须能够外推。我们提出了一种方法，融合了3D推理与自回归建模，以3D一致的方式来描绘大的视图变化，从而实现场景合成。我们证明了相当大的改善，在单一图像的大角度视图合成结果相比，各种方法和可能的变种在模拟和真实的数据集。此外，与其他累积方法相比，我们显示出更高的3D一致性。项目网址：https://crockwell.github.io/pixelsynth/
英文摘要：
Recent advancements in differentiable rendering and 3D reasoning have driven exciting results in novel view synthesis from a single image. Despite realistic results, methods are limited to relatively small view change. In order to synthesize immersive scenes, models must also be able to extrapolate. We present an approach that fuses 3D reasoning with autoregressive modeling to outpaint large view changes in a 3D-consistent manner, enabling scene synthesis. We demonstrate considerable improvement in single image large-angle view synthesis results compared to a variety of methods and possible variants across simulated and real datasets. In addition, we show increased 3D consistency compared to alternative accumulation methods. Project website: https://crockwell.github.io/pixelsynth/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
