AI Paper Atlas

Research map / 3D vision / Face and shape

Texture Fields: Learning Texture Representations in Function Space

Michael Oechsle, Lars Mescheder, Michael Niemeyer, Thilo Strauss, Andreas Geiger

ICCV 2019 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 266 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
use Texture Fields instead of the projection baseline (GT shapes)single-image texture reconstruction · ShapeNet single-image texture reconstruction (GT shapes), meanFID: 25.936 -> 12.036Improved
use Texture Fields instead of the NVS baseline (GT shapes)single-image texture reconstruction · ShapeNet single-image texture reconstruction (GT shapes), meanFID: 27.031 -> 12.036Improved
use Texture Fields instead of NVS (GT shapes)single-image texture reconstruction · ShapeNet single-image texture reconstruction (GT shapes), meanSSIM: 0.938 -> 0.934Hurt
use Texture Fields instead of NVS (GT shapes)single-image texture reconstruction · ShapeNet single-image texture reconstruction (GT shapes), meanFeature-l1: 0.159 -> 0.144Improved
use Texture Fields instead of NVS in the full pipelineOccupancy Networks shape + texture · ShapeNet full pipeline with Occupancy Networks shapes, meanFID: 69.306 -> 51.659Improved
use Texture Fields instead of NVS in the full pipelineOccupancy Networks shape + texture · ShapeNet full pipeline with Occupancy Networks shapes, meanSSIM: 0.867 -> 0.867No clear effect
use Texture Fields instead of NVS in the full pipelineOccupancy Networks shape + texture · ShapeNet full pipeline with Occupancy Networks shapes, meanFeature-l1: 0.225 -> 0.211Improved
use Texture Fields instead of Im2Avatar (cars, full pipeline)textured 3D reconstruction · ShapeNet full pipeline with Occupancy Networks shapes, carsFID: 149.393 -> 77.439Improved
use Texture Fields instead of projection on tables (GT shapes)single-image texture reconstruction · ShapeNet single-image texture reconstruction (GT shapes), tablesFeature-l1: 0.123 -> 0.123No clear effect
use continuous texture field instead of 128^3 voxel representationcat/human single-object fitting · single 3D object overfittinghigh-frequency detail (qualitative)Improved

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