AI Paper Atlas

Research map / Video / Video segmentation and tracking

Free Supervision From Video Games

Philipp Krähenbühl

CVPR 2018 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 95 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 albedo images instead of original images as inputFlowNet 2 · GTA V meanflow accuracy at 5px (%): 48.86 -> 51.30Improved
Use albedo images instead of original images as inputFlowFields · GTA V meanflow accuracy at 5px (%): 37.40 -> 44.46Improved
Use KITTI-trained depth models on GTA VEigen et al. and DiW · GTA VRMSE: Mean depth 7.12; Eigen et al. 7.49; DiW 7.09Hurt
Tune reflectance-filtering parameters for GTA VReflectance filtering · GTA VLMSE: 0.086 -> 0.076Improved
Combine the original image with an additional visual modalityGTA V imitation-learning agent · GTA V car action predictionclassification error (%)Improved
Combine all available modalitiesGTA V imitation-learning agent · GTA V car action predictionclassification error (%)Improved
Use optical flow alone as inputGTA V imitation-learning agent · GTA V car action predictionclassification error (%)Hurt

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