AI Paper Atlas

Research map / 3D vision / Face and shape

Inverse 3D Microscopy Rendering for Cell Shape Inference with Active Mesh

Sacha Ichbiah, Anshuman Sinha, Fabrice Delbary, Hervé Turlier

ICCV 2025 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 5 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
use CUDA GPU implementation of mesh Fourier transform instead of vectorized CPUdeltaMic mesh FT · 80-triangle spherical mesh benchmarkspeed and memory: approx 10^3 speedup on one NVIDIA V100Improved
add narrow-band frequency cutoff (only where PSF FT exceeds 1% of max)deltaMic mesh FT · mesh FT computationcomputational cost: reduces cost by several orders of magnitude (1% threshold)Improved
use deltaMic instead of the active mesh method DM3Dmouse organoid shape inference · 15 mouse organoid 3D imagesMSE, SSIM, PSNR: outperforms DM3D across all metrics (no numbers given in text)Improved
increase initial mesh shift or scale from targetdeltaMic · Spot reference meshconvergence iterationsHurt
add random noise to the target imagedeltaMic · Spot reference meshMSE of reconstructionNo clear effect

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