AI Paper Atlas

Research map / 3D vision / Face and shape

DiViNeT: 3D Reconstruction from Disparate Views using Neural Template Regularization

Aditya Vora, Akshay Gadi Patil, Hao Zhang

NeurIPS 2023 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 1 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 depth constraint to SDF-only constraint (ablation)DiViNeT · DTU sparseChamfer Distance: 2.70 -> 1.96Improved
add SDF constraint to depth-only constraint (full pipeline) (ablation)DiViNeT · DTU sparseChamfer Distance: 1.96 -> 1.52Improved
replace pre-trained TPN (DTU) with TPN re-trained on target data (ablation)DiViNeT · MobileBrick BridgeF1: 0.565 -> 0.658Improved
TPN re-training vs pre-trained on Colosseum (ablation)DiViNeT · MobileBrick ColosseumF1: 0.219 -> 0.22No clear effect
neural template regularization vs MonoSDFDiViNeT · DTU sparse 3-viewChamfer Distance (mean): 1.86 -> 1.77Improved
template regularization vs NeuS in sparse viewsDiViNeT · DTU sparse 3-viewChamfer Distance (mean): 4.78 -> 1.77Improved
template regularization vs COLMAP in sparse viewsDiViNeT · DTU sparse 3-viewChamfer Distance (mean): 2.56 -> 1.77Improved
compare to feature-grid Voxurf with dense viewsDiViNeT · DTU denseChamfer Distance (mean): 0.79 vs 0.76Hurt
template regularization vs NeuS in dense viewsDiViNeT · DTU denseChamfer Distance (mean): 0.84 -> 0.79Improved
compare against GeoNeuS (COLMAP-point regularization) on dense viewsDiViNeT · MobileBrick BridgeF1: 0.74 -> 0.915Improved
compare against GeoNeuS on CastleDiViNeT · MobileBrick CastleF1: 0.457 -> 0.572Improved
compare against MonoSDF on novel view synthesisDiViNeT · DTU 3-view NVSPSNR: 23.64 -> 24.34Improved

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