AI Paper Atlas

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

ST-P3: End-to-End Vision-Based Autonomous Driving via Spatial-Temporal Feature Learning

Shengchao Hu, Li Chen, Penghao Wu, Hongyang Li, Junchi Yan, Dacheng Tao

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 320 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
add Egocentric Aligned Accumulation (ablation)ST-P3 · nuScenes valvehicle IoU: 38.00 -> 38.79Improved
add explicit depth supervision (ablation)ST-P3 · nuScenes valvehicle IoU: 38.79 -> 40.10Improved
add Dual Modelling (ablation)ST-P3 · nuScenes valvehicle PQ: 28.63 -> 31.35Improved
add Dual Modelling (ablation)ST-P3 · nuScenes valvehicle IoU: 37.09 -> 38.16Improved
add loss for all timestamps (LFA) (ablation)ST-P3 · nuScenes valvehicle PQ: 31.35 -> 31.72Improved
add loss for all timestamps (LFA) (ablation)ST-P3 · nuScenes valvehicle IoU: 38.16 -> 38.63Improved
add front-view GRU refinement to the sampler (ablation)ST-P3 · nuScenes valcollision rate (%): 0.850 -> 0.513Improved
add prior-knowledge sampler to the refinement unit (ablation)ST-P3 · nuScenes valcollision rate (%): 1.089 -> 0.513Improved
add front-view GRU refinement to the sampler (ablation)ST-P3 · nuScenes valL2 error (m): 2.128 -> 1.890Improved
use Bernoulli instead of Gaussian future uncertaintyST-P3 · nuScenes valfuture semantic IoU (%): 38.63 -> 38.87No clear effect
replace ground-truth-only vanilla planner with ST-P3 cost-based plannerST-P3 · nuScenes open-loop planningL2 / collision: L2 3s 2.80 -> 2.90; collision 3s 2.76 -> 1.27Mixed
compare ST-P3 with LiDAR-based Transfuser on long routesST-P3 · CARLA Town05 Longdriving score: 33.15 vs 11.45Hurt

Later papers that compared with this method

6 later accepted papers report ST-P3 as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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