SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving

NeurIPSSpotlight2025

Authors
Haiming Zhang, Yiyao Zhu, Wending Zhou, Xu Yan, Yingjie CAI, Bingbing Liu, Shuguang Cui, Zhen Li
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Sparse Perception Models (SPMs) adopt a query-driven paradigm that forgoes explicit dense BEV or volumetric construction, enabling highly efficient computation and accelerated inference…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

efficient

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive