AI Paper Atlas

Research map / 3D vision / Face and shape

NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations

Varun Jampani, Kevis-kokitsi Maninis, Andreas Engelhardt, Arjun Karpur, Karen Truong, Kyle Sargent, Stefan Popov, Andre Araujo, Ricardo Martin Brualla, Kaushal Patel, Daniel Vlasic, Vittorio Ferrari and 4 more

NeurIPS 2023 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 8 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 NAVI GT poses instead of COLMAP poses (ablation)InstantNGP · NAVI multiviewPSNR: 24.04 -> 27.54Improved
use NAVI GT poses instead of COLMAP poses (ablation)InstantNGP · NAVI multiviewSSIM: 0.93 -> 0.94Improved
use NAVI GT poses instead of COLMAP poses (ablation)InstantNGP · NAVI multiviewLPIPS: 0.079 -> 0.045Improved
initialize NeROIC with GT poses instead of COLMAP (ablation)NeROIC · NAVI in-the-wild S_CPSNR: 19.77 -> 22.75Improved
initialize NeRS with GT poses instead of Directions (ablation)NeRS · NAVI in-the-wild S_CPSNR: 18.67 -> 17.92Hurt
initialize SAMURAI with GT poses instead of Directions (ablation)SAMURAI · NAVI in-the-wild S_CPSNR: 25.34 -> 25.65No clear effect
GT pose initialization for NeROIC rotation error (ablation)NeROIC · NAVI in-the-wild S_Crotation error (deg): 42.11 -> 33.17Improved
SAMURAI vs NeRS with Directions initSAMURAI · NAVI in-the-wild S_CPSNR: 18.67 -> 25.34Improved
random initialization (GNeRF) vs pose-informed initGNeRF · NAVI in-the-wild S_CPSNR: 25.34 -> 8.30Hurt
SAMURAI vs NeRS for shape reconstructionSAMURAI · NAVI in-the-wild shapeIoU: 45.1% -> 63.7%Improved
SAMURAI vs NeRS for shape reconstructionSAMURAI · NAVI in-the-wild shapeChamfer distance: 5.86 -> 3.65Improved
learned matching (SuperGlue) vs SIFT + MNNSuperPoint + SuperGlue · NAVI correspondence multiviewPrecision@0.2: 2.8 -> 26.8Improved

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