干旱区生态环境知识资源中心(Arid): Radiative Backpropagation: An Adjoint Method for Lightning-Fast Differentiable Rendering

Arid

DOI	10.1145/3386569.3392406
	Radiative Backpropagation: An Adjoint Method for Lightning-Fast Differentiable Rendering
	Nimier-David, Merlin; Speierer, Sebastien; Ruiz, Benoit; Jakob, Wenzel
通讯作者	Nimier-David, M
来源期刊	ACM TRANSACTIONS ON GRAPHICS
ISSN	0730-0301
EISSN	1557-7368
出版年	2020
卷号	39 期号:4
英文摘要	Physically based differentiable rendering has recently evolved into a powerful tool for solving inverse problems involving light. Methods in this area perform a differentiable simulation of the physical process of light transport and scattering to estimate partial derivatives relating scene parameters to pixels in the rendered image. Together with gradient-based optimization, such algorithms have interesting applications in diverse disciplines, e.g., to improve the reconstruction of 3D scenes, while accounting for interreflection and transparency, or to design meta-materials with specified optical properties. The most versatile differentiable rendering algorithms rely on reverse-mode differentiation to compute all requested derivatives at once, enabling optimization of scene descriptions with millions of free parameters. However, a severe limitation of the reverse-mode approach is that it requires a detailed transcript of the computation that is subsequently replayed to back-propagate derivatives to the scene parameters. The transcript of typical renderings is extremely large, exceeding the available system memory by many orders of magnitude, hence current methods are limited to simple scenes rendered at low resolutions and sample counts. We introduce radiative backpropagation, a fundamentally different approach to differentiable rendering that does not require a transcript, greatly improving its scalability and efficiency. Our main insight is that reverse-mode propagation through a rendering algorithm can be interpreted as the solution of a continuous transport problem involving the partial derivative of radiance with respect to the optimization objective. This quantity is "emitted" by sensors, "scattered" by the scene, and eventually "received" by objects with differentiable parameters. Differentiable rendering then decomposes into two separate primal and adjoint simulation steps that scale to complex scenes rendered at high resolutions. We also investigated biased variants of this algorithm and find that they considerably improve both runtime and convergence speed. We showcase an efficient GPU implementation of radiative backpropagation and compare its performance arid the quality of its gradients to prior work.
英文关键词	Ray Tracing Global Illumination Differentiable Rendering
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000583700300119
WOS类目	Computer Science, Software Engineering
WOS研究方向	Computer Science
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/327196
作者单位	[Nimier-David, Merlin; Speierer, Sebastien; Ruiz, Benoit; Jakob, Wenzel] Ecole Polytech Fed Lausanne EPFL, Lausanne, Switzerland
推荐引用方式 GB/T 7714	Nimier-David, Merlin,Speierer, Sebastien,Ruiz, Benoit,et al. Radiative Backpropagation: An Adjoint Method for Lightning-Fast Differentiable Rendering[J],2020,39(4).
APA	Nimier-David, Merlin,Speierer, Sebastien,Ruiz, Benoit,&Jakob, Wenzel.(2020).Radiative Backpropagation: An Adjoint Method for Lightning-Fast Differentiable Rendering.ACM TRANSACTIONS ON GRAPHICS,39(4).
MLA	Nimier-David, Merlin,et al."Radiative Backpropagation: An Adjoint Method for Lightning-Fast Differentiable Rendering".ACM TRANSACTIONS ON GRAPHICS 39.4(2020).