AI Paper Atlas

Research map / 3D vision / Depth and stereo

Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera

Hongrui Cai, Wanquan Feng, Xuetao Feng, Yan Wang, Juyong Zhang

NeurIPS 2022 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 19 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 NDR instead of RGB-D fusion baselinesDynamic scene reconstruction · DeepDeform Dogmean geometry error: 92.53 -> 3.42Improved
use NDR instead of OcclusionFusionDynamic scene reconstruction · KillingFusion Hatmean geometry error: 6.77 -> 4.93Improved
use NDR instead of OcclusionFusionDynamic scene reconstruction · KillingFusion Alexmean geometry error: 3.75 -> 4.24Hurt
add depth-image supervision to RGB-only NDR (ablation)NDR · DeepDeform and KillingFusion qualitative sequencesreconstruction geometry qualityImproved
add RGB-image and color-loss supervision to depth-only NDR (ablation)NDR · dynamic reconstruction qualitative sequencesgeometric detailImproved
replace the bijective map with 6D motion (ablation)NDR · Rotated Bodycycle consistency error: 5.29 -> 473.25Hurt
replace the bijective map with 6D motion (ablation)NDR · Talking Headcycle consistency error: 4.97 -> 289.41Hurt
remove the topology-aware network F_q (ablation)NDR · topology-varying regions, including human face eyes and mouthtopology-varying geometry and motion qualityHurt
remove the visible loss term (ablation)NDR with depth supervision · depth-only qualitative reconstructionlocal geometry qualityHurt
increase camera-pose initialization noiseNDR · Moving Jointsmean geometry error (mm): 2.95 -> 30.28Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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