AI Paper Atlas

Research map / 3D vision / Depth and stereo

DualResPS: Dual-Resolution Photometric Stereo Using a Frame-Event Hybrid Camera

Haotian Zhuang, Bohan Yu, Zhuofeng Wang, Boxin Shi

ECCV 2026 · 3D vision › Depth and stereo · approach: Non-line-of-sight imaging · 0 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
combine 3 long-exposure frames with event stream instead of 23-frame self-supervised frame-only baselineDualResPS vs LL22a · DiLiGenT (semi-real, average)MAE (degrees): 7.70 -> 7.36Improved
add frames to events (DualResPS instead of events only)EventPS · DiLiGenT (semi-real, average)MAE (degrees): 19.99 -> 7.36Improved
use DualResPS instead of supervised UniMS-PSphotometric stereo · DiLiGenT (semi-real, average)MAE (degrees): 6.95 -> 7.36No clear effect
use DualResPS instead of supervised SDM-UniPS on Ballphotometric stereo · DiLiGenT BallMAE (degrees): 1.83 -> 2.08Hurt
use DualResPS instead of supervised LINO on Harvestphotometric stereo · DiLiGenT HarvestMAE (degrees): 11.33 -> 18.01Hurt
increase number of frames for frame-based methodFramePS · DiLiGenT / DiLiGenT-PiMAE (degrees)Improved

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