AI Paper Atlas

Research map / 3D vision / Depth and stereo

Depth on Demand: Streaming Dense Depth from a Low Frame Rate Active Sensor

Andrea Conti, Matteo Poggi, Valerio Cambareri, Stefano Mattoccia

ECCV 2024 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 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
add multi-view stereo cues to sparse-depth-only DoD (ablation)DoD · ScanNetV2MAE: 0.049 -> 0.041Improved
add sparse depth cues to MVS-only DoD (ablation)DoD · ScanNetV2F-Score: 0.530 -> 0.871Improved
add multi-view stereo cues to sparse-depth-only DoD for 3D reconstruction (ablation)DoD · ScanNetV2F-Score: 0.870 -> 0.871No clear effect
estimate depth at RGB frame rate instead of the depth sensor frame rate (ablation)DoD · ScanNetV2 3D reconstructionF-Score: 0.856 -> 0.871Improved
inject sparse depth into MVS networks with only 2 viewsGuided MVS networks · ScanNetV2MAE: 0.124 -> 0.286 (CAS-MVSNet, 8 to 2 views)Hurt
use DoD instead of single-view depth completion on ScanNetV2temporal depth densification · ScanNetV2MAE: 0.067 -> 0.041Improved
use DoD on KITTI where multi-view overlap is smallDoD · KITTI LiDAR 1HzMAE: 0.348 -> 0.347 vs CompletionFormerNo 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