AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving

Wenchao Sun, Xuewu Lin, Keyu Chen, Zixiang Pei, Xiang LI, Yining Shi, Sifa ZHENG

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 38 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
double static vocabulary size from 1024 to 16384 anchors (ablation)Hydra-MDP · NAVSIM v2EPDMS: 85.02 -> 87.35Improved
scale static vocabulary to 32768 anchors (ablation)Hydra-MDP · NAVSIM v2memory: 16384: 38877 MB -> OOMHurt
increase factorized vocabulary from 512x128 to 1024x256 (ablation)SparseDriveV2 · NAVSIM v2EPDMS: 88.7 -> 90.1Improved
replace multi-head cross-attention with deformable aggregation for path-scene interaction (ablation)SparseDriveV2 · NAVSIM v2EPDMS: 87.7 -> 89.9Improved
add trajectory re-conditioning (with MHA) (ablation)SparseDriveV2 · NAVSIM v2EPDMS: 87.7 -> 89.9Improved
add trajectory re-conditioning (with DFA) (ablation)SparseDriveV2 · NAVSIM v2EPDMS: 89.9 -> 90.1Improved
use SparseDriveV2 scoring with ResNet-34 instead of Hydra-MDP with V2-99Hydra-MDP · NAVSIM v1PDMS: 90.3 -> 92.0Improved
SparseDriveV2 vs ipadipad · NAVSIM v1PDMS: 91.7 -> 92.0Improved
SparseDriveV2 vs HiP-ADHiP-AD · Bench2DriveSuccess Rate (%): 69.09 -> 70.00Improved
SparseDriveV2 vs SimLingoSimLingo · Bench2DriveDriving Efficiency: 259.23 -> 199.84Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy