AI Paper Atlas

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

RAP: 3D Rasterization Augmented End-to-End Planning

Lan Feng, Yang Gao, Eloi Zablocki, Quanyi Li, Wuyang Li, Sichao Liu, Matthieu Cord, Alexandre Alahi

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 33 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 recovery-oriented perturbed ego trajectories (8.5k) (ablation)RAP-DINO · NAVSIM v2 two-stageEPDMS: 32.5 -> 36.9Improved
add recovery-oriented perturbed ego trajectories (8.5k) (ablation)RAP-DINO · NAVSIM v1PDMS: 92.5 -> 92.5No clear effect
use colored cuboid faces rather than transparent (ablation)RAP-ResNet rasterization · NAVSIM navtrain valMinADE: 0.98 -> 0.91Improved
add depth decay in rasterization (ablation)RAP-ResNet rasterization · NAVSIM navtrain valMinADE: 1.05 -> 0.91Improved
use black background instead of natural sky-ground (ablation)RAP-ResNet rasterization · NAVSIM navtrain valMinADE: 1.33 -> 0.91Improved
add spatial and global R2R alignment (ablation)RAP-ResNet · NAVSIM navtrain val (varying real-data fraction)MinADEImproved
align real features to raster features rather than the reverse or symmetric (ablation)R2R alignment · NAVSIM navtrain val, 50% real dataMinADE: 1.12 -> 1.02Improved
scale cross-agent synthetic samples from 1k to 1000k (ablation)RAP-ResNet · NAVSIM navtrain valMinADE: y = -0.021 ln(x) + 1.2173Improved
replace 50% of real data with rasterized samples (with alignment) (ablation)RAP-ResNet · NAVSIM navtrain valMinADEImproved
apply RAP to DiffusionDriveDiffusionDrive · NAVSIM v1 navtestPDMS: 86.0 -> 89.2Improved
apply RAP to iPadiPad · NAVSIM v1 navtestPDMS: 91.7 -> 92.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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