AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception

Jianbing Shen, Chunliang Li, Wencheng Han, Junbo Yin, Sanyuan Zhao

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 8 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
use RepVF unified representation instead of task-specific representations (multi-head) (ablation)multi-task 3D lane + object detection · OpenLane + Waymo 30% subsetF-Score: 58.7 -> 66.4Improved
use a single head instead of multiple heads with RepVF (ablation)RFTR · OpenLane + Waymo 30% subsetVehicle L1 mAP: 22.1 -> 25.3Improved
use a single head instead of multiple heads with RepVF (ablation)RFTR · OpenLane + Waymo 30% subsetF-Score: 66.4 -> 66.5No clear effect
RepVF instead of anchor representation (ablation)3D lane detection · OpenLane (ablation)F-Score: 53.4 -> 66.0Improved
RepVF instead of random point set (ablation)3D lane detection · OpenLane (ablation)F-Score: 58.1 -> 66.0Improved
add simultaneous multi-task training with 3D object detection (ablation)RepVF 3D lane detection · OpenLane (ablation)F-Score: 66.0 -> 66.5Improved
use single-head RFTR instead of multi-head baseline (ablation)multi-task training · gradient disparitymean gradient disparity: 2.98 -> 2.47Improved
use multi-head with RepVF instead of multi-head with task-specific representations (ablation)gradient disparity · gradient disparitymean gradient disparity: 2.98 -> 2.72Improved
use lightweight multi-head with task-specific representation instead of larger head (ablation)multi-head baseline · OpenLane + Waymo 30% subsetF-Score: 58.7 -> 49.6Hurt
use RFTR unified model instead of PETR3D object detection · Waymo val (L1)pedestrian mAP: 12.1 -> 8.0Hurt
use RFTR unified model instead of PETR3D object detection · Waymo val (L1)overall mAP: 20.9 -> 19.5Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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