AI Paper Atlas

Research map / Optimization / Optimizers

Plateau-Reduced Differentiable Path Tracing

CVPR 2023 · Optimization › Optimizers · approach: Constrained and non-backprop training · 17 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
convolve rendering over scene parameters and estimate gradients with the non-differentiable rendererOur_no-grad vs Mitsuba · Cup, Shadows, Occlusion, Global Illumination, Sort, Causticparameter-space MSE: Cup: 5.49×10⁻³ -> 4.92×10⁻⁶; Shadows: 1.64×10⁻³ -> 1.74×10⁻⁵; Occlusion: 5.85×10⁻² -> 2.34×10⁻⁴; Global Illumination: 3.Helped
remove importance sampling (ablation)Our_no-grad · Mean (six tasks)log-relative error ratio: 4.81×; 5.91×Hurt
remove adaptive perturbations (ablation)Our_no-grad · Mean (six tasks)log-relative error ratio: 4.50×; 5.78×Hurt
remove antithetic sampling (ablation)Our_no-grad · Mean (six tasks)log-relative error ratio: 4.78×; 7.06×Hurt
use differentiable-renderer gradients instead of differentiating through perturbationOur method · six optimization tasksparameter-space MSE: Cup: 4.92×10⁻⁶ -> 2.77×10⁻¹; Shadows: 1.74×10⁻⁵ -> 1.28×10⁰; Occlusion: 2.34×10⁻⁴ -> 1.87×10¹; Global Illumination: 5.07Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy