Joint Sampling and Optimisation for Inverse Rendering
When dealing with difficult inverse problems such as inverse rendering, using Monte Carlo estimated gradients to optimise parameters can slow down convergence due to variance. Averaging many gradient samples in each iteration reduces this variance trivially. However, for problems that require thousands of optimisation iterations, the computational cost of this approach rises quickly. We derive a theoretical framework for interleaving sampling and optimisation. We update and reuse past samples with low-variance finite-difference estimators that describe the change in the estimated gradients between each iteration. By combining proportional and finite-difference samples, we continuously reduce the variance of our novel gradient meta-estimators throughout the optimisation process. We investigate how our estimator interlinks with Adam and derive a stable combination. We implement our method for inverse path tracing and demonstrate how our estimator speeds up convergence on difficult optimisation tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Inverse RenderingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
NeRF as a Non-Distant Environment Emitter in Physics-based Inverse Rendering
Physics-based inverse rendering enables joint optimization of shape, material, and lighting based on captured 2D images. To ensure accurate reconstruction, using a light model that closely resembles the captured environm…
Inverse RenderingNeRFPIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance Regularization
This paper addresses the problem of inverse rendering from photometric images. Existing approaches for this problem suffer from the effects of self-shadows, inter-reflections, and lack of constraints on the surface refle…
Inverse RenderingPositionShape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising
Recent advances in differentiable rendering have enabled high-quality reconstruction of 3D scenes from multi-view images. Most methods rely on simple rendering algorithms: pre-filtered direct lighting or learned represen…
3D ReconstructionDenoisingDepth PredictionImage Relighting+3NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination
Inverse rendering methods aim to estimate geometry, materials and illumination from multi-view RGB images. In order to achieve better decomposition, recent approaches attempt to model indirect illuminations reflected fro…
Depth PredictionImage RelightingInverse RenderingSurface Normals Estimation+1NDJIR: Neural Direct and Joint Inverse Rendering for Geometry, Lights, and Materials of Real Object
The goal of inverse rendering is to decompose geometry, lights, and materials given pose multi-view images. To achieve this goal, we propose neural direct and joint inverse rendering, NDJIR. Different from prior works wh…
Inverse Rendering