AI Paper Atlas

Research map / 3D vision / Face and shape

CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction

Ziyue Feng, Liang Yang, Pengsheng Guo, Bing Li

ICCV 2023 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 24 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
replace back-projected 2D image features with grid-sampled standard cost volume (ablation)CVRecon on VoRTX · ScanNet2F1-Score: 0.703 -> 0.711Improved
add Camera Ray Compensation to the cost volume (ablation)CVRecon on VoRTX · ScanNet2F1-Score: 0.711 -> 0.728Improved
add Contextual Compensation by concatenating 2D keyframe feature (ablation)CVRecon on VoRTX · ScanNet2F1-Score: 0.728 -> 0.730Improved
fuse contextual feature with a single shared 2D conv instead of concat only (ablation)CVRecon on VoRTX · ScanNet2F1-Score: 0.730 -> 0.731No clear effect
use group convolution with separate weights per depth plane instead of shared conv (ablation)CVRecon on VoRTX · ScanNet2F1-Score: 0.730 -> 0.735Improved
build ray context from all 7 cost-volume channels instead of one (ablation)Ray Compensation · ScanNet2F1-Score: +0.002 F1 with 7 times memoryNo clear effect
replace back-projected features with RCCV in AtlasAtlas · ScanNet2F1 Score: 0.596 -> 0.648Improved
replace back-projection with RCCV in VoRTX (CVRecon)VoRTX · ScanNet2 (Atlas protocol)F1 Score @ 5cm: 0.641 -> 0.690Improved
compare volumetric CVRecon with depth-based SimpleRecon on completenessCVRecon · ScanNet2 (TransformerFusion protocol)Completeness: 0.060 (SimpleRecon) vs 0.067 (CVRecon)Hurt

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