Abstract

Recent differentiable rendering techniques have become key tools to tackle many inverse problems in graphics and vision. Existing models, however, assume steady-state light transport, i.e., infinite speed of light. While this is a safe assumption for many applications, recent advances in ultrafast imaging leverage the wealth of information that can be extracted from the exact time of flight of light. In this context, physically-based transient rendering allows to efficiently simulate and analyze light transport considering that the speed of light is indeed finite. In this paper, we introduce a novel differentiable transient rendering framework, to help bring the potential of differentiable approaches into the transient regime. To differentiate the transient path integral we need to take into account that scattering events at path vertices are no longer independent; instead, tracking the time of flight of light requires treating such scattering events at path vertices jointly as a multidimensional, evolving manifold. We thus turn to the generalized transport theorem, and introduce a novel correlated importance term, which links the time-integrated contribution of a path to its light throughput, and allows us to handle discontinuities in the light and sensor functions. Last, we present results in several challenging scenarios where the time of flight of light plays an important role such as optimizing indices of refraction, non-line-of-sight tracking with nonplanar relay walls, and non-line-of-sight tracking around two corners.

Highlights

  • Physically-based differentiable rendering deals with the computation of the derivatives of radiometric measurements, according to changes in scene parameters

  • While several special-purpose differentiable rendering systems have been proposed in the past (e.g., [Chen et al 2019; Gkioulekas et al 2016; Kato et al 2018; Liu et al 2019b]) in this work we focus on general-purpose differentiable rendering

  • We introduce here the main aspects of both the transient path integral and path-space differentiable rendering

Read more

Summary

Introduction

Physically-based differentiable rendering deals with the computation of the derivatives of radiometric measurements, according to changes in scene parameters (see recent references [Kato et al 2020; Zhao et al 2020] for a wide overview of the field). It has recently become a key tool for inverse rendering or scene reconstruction problems that require gradient-based optimization, and to enable the integration of physics-based simulations in machine learning pipelines, computing the loss function in rendering space. We introduce here the main aspects of both the transient path integral and path-space differentiable rendering. ΩT where T represents the space of temporal delays, t = t0...tk is the sequence of time delays on each vertex, dμ (t) denotes temporal integration at each vertex, dμ (x) is the differential measure, and x = x0...xk is a path of k + 1 vertices.

Objectives
Results
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call