期刊
COMPUTER GRAPHICS FORUM
卷 41, 期 4, 页码 129-138出版社
WILEY
DOI: 10.1111/cgf.14592
关键词
-
资金
- NSF [1900783, 1900849, 1900927]
- Sloan Research Fellowship
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1900849] Funding Source: National Science Foundation
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1900783, 1900927] Funding Source: National Science Foundation
Mathematical representation of object shape is crucial for solving inverse rendering problems. Explicit representations are efficient for differentiable rendering but have difficulty handling topology changes. Implicit representations offer better support for topology changes but are harder to use for physics-based differentiable rendering. We introduce a new physics-based inverse rendering pipeline that utilizes both implicit and explicit representations. Our technique combines the benefits of both representations by supporting topology changes and differentiable rendering of complex effects.
Mathematically representing the shape of an object is a key ingredient for solving inverse rendering problems. Explicit representations like meshes are efficient to render in a differentiable fashion but have difficulties handling topology changes. Implicit representations like signed-distance functions, on the other hand, offer better support of topology changes but are much more difficult to use for physics-based differentiable rendering. We introduce a new physics-based inverse rendering pipeline that uses both implicit and explicit representations. Our technique enjoys the benefit of both representations by supporting both topology changes and differentiable rendering of complex effects such as environmental illumination, soft shadows, and interreflection. We demonstrate the effectiveness of our technique using several synthetic and real examples.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据