AI Paper Atlas

Research map / 3D vision / Face and shape

Disorder-Invariant Implicit Neural Representation

Hao Zhu, Shaowen Xie, Zhen Liu, Fengyi Liu, Qi Zhang, You Zhou, Yi Lin, Zhan Ma, Xun Cao

TPAMI 2024 · 3D vision › Face and shape · approach: Implicit neural representation design · 25 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
add hash-table to SIREN backbone (ablation)SIREN · 2D image fittingPSNR: increased 30dBImproved
add hash-table to PE+MLP/MLP backbone (ablation)MLP · 2D image fittingPSNR: increased 17dBImproved
DINER (MLP) versus InstantNGPDINER MLP · 2D image fittingPSNR: advantage of 6dBImproved
increase hash-table width up to number of image channels (ablation)DINER · 2D image fitting 1/2/3-channelPSNRImproved
increase hash-table width beyond number of channels (ablation)DINER · 2D image fittingPSNRNo clear effect
increase hash-table width up to rank of linearly dependent channels (ablation)DINER · Multispectral 6- and 7-channel imagesPSNRImproved
use SIREN backbone instead of MLP in DINER at 10000 epochs (ablation)DINER · 2D image fittingPSNR: 59.64dB vs 59.53dBNo clear effect
DINER instead of NeRV on video representationDINER · UVG video fittingPSNR: 36.08 dB -> 50.74 dBImproved
DINER instead of SIREN on video representation (ablation)SIREN 4x64 · UVG video fittingPSNR: 21.22 dB -> 50.74 dBImproved
add hash-table to SIREN on video (ablation)SIREN · UVG video fittingtraining time: 706s -> 1309sHurt
DINER instead of DeCAF for refractive index recoveryDINER · Granulocyte phantomtraining time: 401 minutes -> 91 minutesImproved
DINER instead of PhysenNet in lensless imagingDINER · Real lensless imagingPSNR: >7 dBImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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