atlas

Research map / 3D vision / Face and shape

Two-Shot Spatially-Varying BRDF and Shape Estimation

CVPR 2020 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 74 citations (OpenAlex)

Check 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
Use guided stage-wise cascaded estimation with joint refinement instead of a single joint network (ablation)Two-Shot Spatially-Varying BRDF and Shape Estimation · 20 unseen synthetic objectsNormal MSE: 0.025 -> 0.021Helped
Use MergeConv blocks rather than standard convolutions for shape estimation (ablation)Shape estimation network · Synthetic shape estimationDepth MSE: 0.021 to 0.016Helped
Use MergeConv blocks rather than standard convolutions for shape estimation (ablation)Shape estimation network · Synthetic shape estimationNormal MSE: 0.026 to 0.021Helped
Use two-shot flash and no-flash inputs instead of a single flash imageSVBRDF and shape estimation · Real-world two-shot imagesVisual reconstruction qualityHelped

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