atlas

Research map / 3D vision / Depth and stereo

Unsupervised Cross-Spectral Stereo Matching by Learning to Synthesize

AAAI 2019 · 3D vision › Depth and stereo · approach: Learned stereo with specialized sensors · 30 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 spectral translation to the stereo matcher (ablation)Only SMN · PittsStereo-RGBNIR Meandisparity RMSE: 1.27 -> 1.18Helped
Replace original CycleGAN with F-cycleGAN for spectral translation (ablation)STN + SMN · PittsStereo-RGBNIR Meandisparity RMSE: 1.18 -> 1.04Helped
Add the auxiliary loss for spectral translation (ablation)STN(F) + SMN · PittsStereo-RGBNIR Meandisparity RMSE: 1.04 -> 0.84Helped
Use concatenated original and translated image pairs rather than original image pairs as SMN inputs (ablation)STN(F) + SMN(aux)(ori) · PittsStereo-RGBNIR Meandisparity RMSE: 0.87 -> 0.84Helped
Use F-cycleGAN with joint training and auxiliary lossCross-spectral stereo matching · PittsStereo-RGBNIRdisparity RMSEMixed

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