AI RESEARCH
Object-Centric Stereo Ranging for Autonomous Driving: From Dense Disparity to Census-Based Template Matching
arXiv CS.CV
•
ArXi:2604.07980v1 Announce Type: new Accurate depth estimation is critical for autonomous driving perception systems, particularly for long range vehicle detection on highways. Traditional dense stereo matching methods such as Block Matching (BM) and Semi Global Matching (SGM) produce per pixel disparity maps but suffer from high computational cost, sensitivity to radiometric differences between stereo cameras, and poor accuracy at long range where disparity values are small.