📝 Publications

📷 3D Vision

AAAI 2026 (Oral)
sym

Real-Time 3D Object Detection with Inference-Aligned Learning
Chenyu Zhao, Xianwei Zheng, Zimin Xia, Linwei Yue, Nan Xue

[ Paper ] [ Code ]

  • SR3D targets the prevalent training-inference gap in 3D object detection.
  • SR3D is a simple yet effective framework that prioritizes robust geometric perception and ranking awareness for reliable 3D detection.