AI Paper Atlas

Research map / 3D vision / Face and shape

Rethinking Directional Parameterization in Neural Implicit Surface Reconstruction

Zijie Jiang, Tianhan Xu, Hiroharu Kato

ECCV 2024 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 3 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
replace viewing direction with reflection direction (ablation)NeuS · DTU (15 scenes)Chamfer distance (total avg): 0.77 -> 1.11Hurt
use hybrid direction instead of viewing directionNeuS · DTU (15 scenes)Chamfer distance (total avg): 0.77 -> 0.72Improved
use hybrid direction instead of viewing directionNeuDA · DTU (15 scenes)Chamfer distance (total avg): 0.67 -> 0.63Improved
use hybrid direction instead of viewing direction on diffuse objectsNeuS · DTU (diffuse scenes)Chamfer distance (avg): 0.67 -> 0.67No clear effect
use hybrid direction instead of viewing direction on specular objectsNeuS · DTU (specular scenes)Chamfer distance (avg): 1.03 -> 0.86Improved
use hybrid direction instead of reflection directionNeuS · Shiny Blender (coffee)Acc.: 3.30 -> 0.64Improved
use hybrid direction instead of viewing directionNeuS · Shiny Blender (4 objects)Acc.: 2.76 -> 0.45Improved
replace viewing direction with reflection direction (ablation)NeuS · Shiny Blender (4 objects)Acc.: 2.76 -> 1.12Improved
use hybrid direction instead of reflection directionNeuDA · Shiny Blender (4 objects)Acc.: 1.41 -> 0.61Improved
set a low initial value of gamma_bOurs (NeuDA) · DTUreconstruction quality (qualitative)Hurt
detach the SDF gradient in the blend weightOurs (NeuDA) · DTUreconstruction quality (qualitative)Improved
fuse view and reflection directions before positional encoding rather than afterOurs (NeuDA) · DTUreconstruction quality (qualitative)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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