Fine-Grained Pillar Feature Encoding Via Spatio-Temporal Virtual Grid for 3D Object Detection

1 code implementation • 11 Mar 2024 • Konyul Park, Yecheol Kim, Junho Koh, Byungwoo Park, Jun Won Choi

Through STV grids, points within each pillar are individually encoded using Vertical PFE (V-PFE), Temporal PFE (T-PFE), and Horizontal PFE (H-PFE).

3D Object Detection Autonomous Vehicles +2