AI Paper Atlas

Research map / 3D vision / Depth and stereo

Compressive Single-Photon 3D Cameras

Felipe Gutierrez-Barragan, Atul Ingle, Trevor Seets, Mohit Gupta, Andreas Velten

CVPR 2022 · 3D vision › Depth and stereo · approach: Spike and event camera reconstruction · 27 citations (OpenAlex)

Check 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 Gray-based Fourier coding instead of truncated Fourier codingCSPH depth estimation · Simulated direct-only scenes across SBR and photon countsrelative mean depth errorImproved
Use Continuous Gray coding at K=8 rather than other K=8 CSPH schemesCSPH depth estimation · Simulated scenes at 128x compressionrelative mean depth error: εdiff ≤0.01%Mixed
Use Gray-based Fourier coding with K≥16CSPH depth estimation · Simulated scenes with SBR and photon counts greater than ∼0.1 and ∼1000relative mean depth error: εdiff ≤0.01%Improved
Increase the number of coding rows K (ablation)CSPH coding schemes · Simulated scenesrelative mean depth errorImproved
Use a wider laser pulse (ablation)CSPH imaging · Wide-pulse simulationsrelative mean depth error difference from full-resolution histogramImproved
Replace Gray-based Fourier coding with truncated Fourier codingCSPH depth estimation · Flash kitchen and bathroom scenes with indirect reflectionsmean absolute depth error: 14 -> 16; 11 -> 14Hurt
Use Continuous Gray coding instead of Gray-based Fourier codingCSPH depth estimation · Scanning-based real-world datamean absolute depth error (mm): 6 -> 7Mixed
Use Gray-based Fourier coding instead of truncated Fourier codingCSPH depth estimation · Scanning-based real-world data with indirect reflectionsmean absolute depth error (mm): 9 -> 6Improved
Use coarse histograms instead of Gray-based Fourier codingCSPH depth estimation · Scanning-based real-world datamean absolute depth error (mm): 6 -> 23Hurt
Transfer only K timestamps rather than use a CSPHSPAD-based 3D camera · Photon-starved simulations with SBR > 1depth estimation performanceMixed
Use coarse histogramming rather than carefully designed Gray- or Fourier-based CSPHSPAD-based 3D camera · Simulated scenes across SBR and photon countsdepth estimation performanceHurt
Use a coding matrix with higher-frequency functionsCSPH in scenes with diffuse indirect reflections · Real-world scanning and flash illuminationdepth estimation accuracyImproved

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