AI Paper Atlas

Research map / 3D vision / Face and shape

Coordinate Quantized Neural Implicit Representations for Multi-view Reconstruction

Sijia Jiang, Jing Hua, Zhizhong Han

ICCV 2023 · 3D vision › Face and shape · approach: Implicit neural representation design · 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
add quantized coordinates to UNISURFUNISURF · DTU (15 scans)mean Chamfer distance: 1.02 -> 0.80Improved
add quantized coordinates to NeuSNeuS · DTU (15 scans)mean Chamfer distance: 0.87 -> 0.73Improved
add quantized coordinates to Geo-NeuSGeo-NeuS · DTU (15 scans)mean Chamfer distance: 0.62 -> 0.60Improved
add quantized coordinates to MonoSDFMonoSDF · ReplicaF-score: 86.18 -> 90.16Improved
use a very high quantization resolution (R=51200) rather than low (1024) (ablation)UNISURF with quantized coordinates · DTU subsetChamfer distance: 1.67 -> 0.59Improved
increase resolution beyond optimum to 102400 (ablation)UNISURF with quantized coordinates · DTU subsetChamfer distance: 0.59 -> 0.69Hurt
replace nearest interpolation with trilinear interpolation (ablation)UNISURF with quantized coordinates · DTU subsetChamfer distance: 0.592 -> 0.72Hurt
use discrete coordinates together with their own positional encodings (not mixed with continuous) (ablation)UNISURF with quantized coordinates · DTU subsetChamfer distance: 0.75 -> 0.592Improved
extract meshes with discrete instead of continuous coordinates in marching cubes (ablation)UNISURF with quantized coordinates · DTU subsetChamfer distance: 0.592 -> 0.586No clear effect
add quantized coordinates to HF-NeuS with higher-frequency positional encodingHF-NeuS · DTU (4 scans, higher-frequency PE)mean Chamfer distance: 1.25 -> 1.05Improved
add quantized coordinates (runtime cost)NeuS · DTU, 1000 iterationsruntime: 104.726 -> 104.591No clear effect
add quantized coordinates to NeuS on scan 83NeuS · DTU scan 83Chamfer distance: 1.01 -> 1.40Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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