AI Paper Atlas

Research map / 3D vision / Depth and stereo

Shape from Heat Conduction

Sriram Narayanan, Mani Ramanagopal, Mark Sheinin, Aswin C. Sankaranarayanan, Srinivasa G. Narasimhan

ECCV 2024 · 3D vision › Depth and stereo · approach: Non-line-of-sight imaging · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
approximate volumetric heat transport by a surface model with average thicknessheat equation simulation · tetrahedral simulations, thickness up to 1 cmpercentage error in thermal video: lower than 5% for thickness up to 1 cm; upper bound 8% up to 20 cmImproved
add camera ray constraint and optimize per-pixel depthshape from Laplacian · shape recoveryambiguity of shapeImproved
add half-space hinge loss from absorbed heat flux of two light sourcesshape from Laplacian · shape recoveryconvex/concave ambiguityImproved
add coarse-to-fine refinement starting from downsampled coarse meshshape from Laplacian · shape recovery from noisy thermal videolow-frequency shape fidelityImproved
use thermal imaging instead of visible-light scanning for transparent/dark objectsshape recovery · transparent bearrecoverability: 1.7 mm error vs SFM scanImproved
increase object thickness in simulation (Stanford Bunny)surface approximation method · simulated bunny at 1 cm, 10 cm, 20 cmshape detailHurt

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