AI Paper Atlas

Research map / Point clouds / Point cloud classification

TopoHR: Hierarchical Centerline Representation for Cyclic Topology Reasoning in Driving Scenes with Point-to-Instance Relations

Yifeng Bai, Zhirong Chen, Bo Song, Erkang Cheng, Haibin Ling

CVPR 2026 · Point clouds › Point cloud classification · approach: Equivariant point cloud networks · 0 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 point-level queries to instance queries (ablation)TopoHR representation · OpenLane-V2 subset_A (ablation)DET_l: 26.8 -> 19.6Hurt
add P2P constrained relation mask (ablation)Ins+Pts · OpenLane-V2 subset_A (ablation)DET_l: 19.6 -> 20.1Improved
add hierarchical integrator (ablation)Ins+Pts+P2P · OpenLane-V2 subset_A (ablation)DET_l: 20.1 -> 32.2Improved
add discrete distance transform segmentation instead of binary segmentation GT (ablation)TopoHR · OpenLane-V2 subset_A (ablation)DET_l: 32.6 -> 34.6Improved
use distance transform instead of binary mask (ablation)TopoHR · OpenLane-V2 subset_A (ablation)DET_l: 32.6 -> 32.0No clear effect
add I2I cyclic forward and backward feedback (ablation)TopoHR instance queries · OpenLane-V2 subset_A (ablation)DET_l: 34.8 -> 35.6Improved
add point queries and P2I relations to the cyclic pipeline (ablation)TopoHR · OpenLane-V2 subset_A (ablation)TOP_lt: 32.9 -> 34.6Improved
replace focal loss with adaptive topological loss (ablation)TopoHR · OpenLane-V2 subset_A (ablation)DET_l: 34.9 -> 36.1Improved
use dice loss instead of focal loss for topology (ablation)TopoHR · OpenLane-V2 subset_A (ablation)DET_l: 34.9 -> 30.4Hurt
raise lambda_pos from 200 to 400 in ATL (ablation)TopoHR · OpenLane-V2 subset_A (ablation)DET_l: 33.8 -> 36.1Improved
raise lambda_neg from 5 to 10 in ATL (ablation)TopoHR · OpenLane-V2 subset_A (ablation)DET_l: 36.1 -> 34.0Hurt
extend training from 24 to 48 epochs (ablation)TopoHR-L · OpenLane-V2 subset_BTOP_ll: 35.8 -> 39.7Improved

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