AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Efficient Photometric Feature Transform for Multi-View Stereo

Kaizhang Kang, Cihui Xie, Ruisheng Zhu, Xiaohe Ma, Ping Tan, Hongzhi Wu, Kun Zhou

ICCV 2021 · 3D vision › Depth and stereo · approach: Photometric stereo · 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
add intensity-insensitive branch to intensity-sensitive branch (bandwidth 6) (ablation)photometric feature network · training lossL_main: 53.98 -> 11.33Improved
add intensity-insensitive branch (bandwidth 8) (ablation)photometric feature network · training lossL_main: 53.31 -> 10.33Improved
add intensity-insensitive branch (bandwidth 10) (ablation)photometric feature network · training lossL_main: 53.17 -> 9.45Improved
increase number of measurements (bandwidth 6 to 10) (ablation)full network · training lossL_main: 11.33 -> 9.45Improved
use learned photometric features instead of CasMVSNetmulti-view stereo on lightstage data · Foxcompleteness at 1mm (%): 34.2 -> 71.9Improved
use learned features instead of COLMAP on full-on lighting imagesCOLMAP pipeline · Catcompleteness at 1mm (%): 05.7 -> 83.6Improved
use learned features instead of COLMAP on full-on lighting imagesCOLMAP pipeline · Roosteraccuracy at 1mm (%): 70.6 -> 65.3Hurt
use learned features instead of COLMAP on full-on lighting imagesCOLMAP pipeline · Cupaccuracy at 1mm (%): 51.4 -> 44.6Hurt
add intensity-insensitive branch to sensitive-only network (ablation)photometric feature network · synthetic ballfeature discriminationImproved
add noise with 5 times training magnitude (5% vs 1%)learned features · geometric reconstructionreconstruction qualityNo clear effect

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