BriefGPT.xyz
Jul, 2018
通过视角合成实现分层结构化三维场景推断
Layer-structured 3D Scene Inference via View Synthesis
HTML
PDF
Shubham Tulsiani, Richard Tucker, Noah Snavely
TL;DR
该研究提出了一种从单个输入图像中推断出场景的分层结构3D表示的方法，使用视图合成作为代理任务来弥补直接监督缺失的不足，并展示了其在两种不同场景下的定性和定量验证结果。
Abstract
We present an approach to infer a layer-structured
3d representation
of a scene from a single input image. This allows us to infer not only the
depth
of the visible pixels, but also to capture the
→