AI Paper Atlas

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

Dense RepPoints: Representing Visual Objects with Dense Point Sets

Ze Yang, Yinghao Xu, Han Xue, Zheng Zhang Raquel Urtasun, Liwei Wang, Stephen Lin, Han Hu

ECCV 2020 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 55 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 distance transform sampling instead of boundary sampling at many points (ablation)Dense RepPoints · COCO val mask AP, n=729mask AP: 24.1 -> 33.8Improved
use distance transform sampling instead of boundary sampling at few points (ablation)Dense RepPoints · COCO val mask AP, n=9mask AP: 19.7 -> 13.9Hurt
use distance transform sampling instead of grid sampling (ablation)Dense RepPoints · COCO val mask AP, n=9mask AP: 5.0 -> 13.9Improved
use distance transform sampling instead of grid sampling (ablation)Dense RepPoints · COCO val mask AP, n=729mask AP: 32.8 -> 33.8Improved
use triangulation instead of concave hull post-processing (ablation)Dense RepPoints with DTS · COCO val mask AP, n=225mask AP: 23.4 -> 32.8Improved
use set-to-set Chamfer supervision instead of point-to-point (ablation)Dense RepPoints with DTS · COCO val mask AP, n=9mask AP: 10.7 -> 13.9Improved
use set-to-set Chamfer supervision instead of point-to-point (ablation)Dense RepPoints with DTS · COCO val mask AP, n=729mask AP: 32.6 -> 33.8Improved
add group pooling and shared offset fields (ablation)RepPoints · COCO val G FLOPS, n=81G FLOPS: 409.46 -> 212.60Improved
add group pooling and shared offset fields (ablation)RepPoints · COCO val detection mAP, n=81box mAP: 37.5 -> 37.5No clear effect
increase number of points from 81 to 729 (ablation)Dense RepPoints · COCO val mask APmask AP: 31.5 -> 33.8Improved
add instance mask supervision (Dense RepPoints) to detection (ablation)Dense RepPoints · COCO val detection mAP, n=81box mAP: 37.5 -> 39.4Improved
add instance mask branch to Faster R-CNN (Mask R-CNN) (ablation)Mask R-CNN · COCO val detection mAPbox mAP: 36.4 -> 37.3Improved

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