AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Learning Adaptive Tensorial Density Fields for Clean Cryo-ET Reconstruction

YUANHAO WANG, Ramzi Idoughi, Wolfgang Heidrich

NeurIPS 2023 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 0 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
increase tensor dimension from 10 to 22 (ablation)Adaptive TensorDF · Simulated tomogram3D PSNR: 35.86 -> 37.45Improved
increase tensor dimension from 22 to 30 (ablation)Adaptive TensorDF · Simulated tomogram3D PSNR: 37.45 -> 37.12Hurt
increase tensor dimension from 22 to 26 (ablation)Adaptive TensorDF · Simulated tomogram3D SSIM: 0.820 -> 0.747Hurt
increase feature size from 4 to 16 (ablation)Adaptive TensorDF · Simulated tomogram3D PSNR: 37.21 -> 37.86Improved
increase feature size from 16 to 20 (ablation)Adaptive TensorDF · Simulated tomogram3D SSIM: 0.837 -> 0.822Hurt
add isotropic Fourier prior to TensoRF (ablation)TensoRF · EMPIAR 10643-40CNR: 0.4123 -> 0.4470Improved
add isotropic Fourier prior to TensoRF (ablation)TensoRF · EMPIAR 10643-40ENL: 48.293 -> 69.483Improved
add TV loss to TensoRF (ablation)TensoRF · EMPIAR 10643-40CNR: 0.2884 -> 0.4123Improved
add TV loss to TensoRF (ablation)TensoRF · EMPIAR 10643-51ENL: 21.120 -> 24.419Improved
replace global TensoRF planes with quadtree adaptive local tensors plus priors (ablation)TensoRF with Fourier prior · EMPIAR 10643-40CNR: 0.4470 -> 0.6808Improved
replace global TensoRF planes with quadtree adaptive local tensors plus priors (ablation)TensoRF with Fourier prior · EMPIAR 10643-51ENL: 25.256 -> 66.015Improved
Adaptive TensorDF versus I-NGPAdaptive TensorDF · EMPIAR 10643-40ENL: 52.231 -> 114.400Improved

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