AI Paper Atlas

Research map / 3D vision / Depth and stereo

Resolving Scale Ambiguity in Multi-view 3D Reconstruction using Dual-Pixel Sensors

Kohei Ashida, Hiroaki Santo, Fumio Okura, Yasuyuki Matsushita

ECCV 2024 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 4 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 DP defocus blur plus SfM/MVS depth instead of monocular metric depth (ZoeDepth) for scalescale estimation · 6 scenes, DSLR and smartphoneaverage error of scale ratios: 0.679 -> 0.219Improved
Change the lens focal length (35mm, 50mm, 85mm)DP scale estimation · 6 scenesaverage error of scale ratiosNo clear effect
Use a small aperture (f/8.0) instead of larger aperturesDP scale estimation · DSLR scenes 4-5average error of scale ratios: 0.135 -> 0.396 (35mm, f/4.0 vs f/8.0)Hurt
Textureless or repetitive-texture scene hurts blur size estimationDP scale estimation · Scene 3, 50mm f/4.0scale ratio: scale ratio 1.352Hurt
Use different image sets for repeated scale estimationDP scale estimation · Scene 1, 35mm f/1.4scale ratio: 1.158 to 1.255Mixed

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