AI Paper Atlas

Research map / 3D vision / Face and shape

Learning To Predict Scene-Level Implicit 3D From Posed RGBD Data

Nilesh Kulkarni, Linyi Jin, Justin Johnson, David F. Fouhey

CVPR 2023 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 2 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 posed RGBD supervision instead of mesh supervision for DRDF trainingD2-DRDF vs. Mesh DRDF · Matterport3DScene F1: 71.9 -> 72.1Improved
Use posed RGBD supervision instead of mesh supervision for DRDF trainingD2-DRDF vs. Mesh DRDF · Matterport3DRay Occ. F1: 27.3 -> 25.1Hurt
Predict a DRDF rather than a density fieldRGBD-supervised reconstruction · Matterport3DRay Occ. F1: 17.9 -> 25.1Improved
Use RGBD supervision rather than ODS mesh supervision with 50% of viewsDRDF training · Matterport3D, 50% viewsScene F1: 68.4 -> 70.0Improved
Use RGBD supervision rather than ODS mesh supervision with 25% of viewsDRDF training · Matterport3D, 25% viewsScene F1: 66.8 -> 70.0Improved
Use RGBD supervision rather than ODS mesh supervision with 3% of viewsDRDF training · Omnidata, 3% viewsRay Occ. F1: 20.3 -> 26.7Improved
Add the sign entropy loss (ablation)D2-DRDF · Scene reconstructionScene F1: 2 pointsImproved
Adapt the pretrained full model using three auxiliary RGBD views and a reference viewD2-DRDF · Few-view adaptationRay Occ. F1: 11.2 -> 34.9Improved
Start adaptation from the depth-pretrained first-stage model rather than the full pretrained model (ablation)D2-DRDF adaptation · Few-view adaptationRay Occ. F1: 34.9 -> 26.0Hurt
Adapt from scratch rather than starting with the full pretrained model (ablation)D2-DRDF adaptation · Few-view adaptationRay Occ. F1: 34.9 -> 25.4Hurt

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