4 papers
LetOccVote: Learning Weakly Supervised 3D Occupancy through Consensus
Chi Zhang, Qi Song, Feifei Li +2
Weakly supervised 3D occupancy prediction reduces the reliance on costly 3D annotations by learning from 2D pseudo-labels generated by vision foundation models. However, existing m…
PoI: A Filter to Extract Pixel of Interest from Novel Views for Scene Coordinate Regression
Feifei Li, Qi Song, Chi Zhang +2
Neural View Synthesis (NVS) techniques such as NeRF and 3D Gaussian Splatting (3DGS) have enabled photorealistic rendering from novel viewpoints and are increasingly used to augmen…
ROA-BEV: 2D Region-Oriented Attention for BEV-based 3D Object Detection
Jiwei Chen, Yubao Sun, Laiyan Ding +1
Vision-based Bird's-Eye-View (BEV) 3D object detection has recently become popular in autonomous driving. However, objects with a high similarity to the background from a camera pe…
Improving Hierarchical Representations of Vectorized HD Maps with Perspective Clues
Chi Zhang, Qi Song, Feifei Li +2
The construction of vectorized High-Definition (HD) maps from onboard surround-view cameras has become a significant focus in autonomous driving. However, current map vector estima…