AI Paper Atlas

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

H^2A^2: Homogeneity-Aware and Heterogeneity-Aware Feature Perception for Unified Indoor 3D Object Detection

Tao Xie, Tao An, Feng Liu, Wensheng Jin, Zhengyu Li, Lijun Zhao, Ruifeng Li

CVPR 2026 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection

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 SF-KS (structural-feature-aware kernel selection) (ablation)TR3D-based backbone · ScanNet v2mAP@0.5: 54.6 -> 61.3Improved
add SF-KS (ablation)TR3D-based backbone · S3DISmAP@0.5: 56.8 -> 56.0Hurt
add NGH (norm-based gradient homogenization) (ablation)TR3D-based backbone · ScanNet v2mAP@0.25: 70.8 -> 72.9Improved
add NGH on top of SF-KS (ablation)H2A2 · ScanNet v2mAP@0.5: 61.3 -> 63.8Improved
add NGH on top of SF-KS (ablation)H2A2 · SUN RGB-DmAP@0.5: 48.1 -> 51.4Improved
add task-aware linear modulation (TLM) (ablation)H2A2 · ScanNet v2mAP@0.25: 76.7 -> 77.5Improved
use TLM instead of linear attention (ablation)H2A2 · S3DISmAP@0.5: 58.8 -> 59.3Improved
port SF-KS and NGH to FCAF3D (ablation)FCAF3D · ScanNet v2mAP@0.5: 57.3 -> 60.6Improved
port SF-KS and NGH to FCAF3D (ablation)FCAF3D · S3DISmAP@0.25: 66.7 -> 70.1Improved
use H2A2 instead of TR3D for zero-shot transferTR3D trained on ScanNet · 3RScan zero-shotmAP@0.25: 47.6 -> 50.7Improved
add H2A2 modules to TR3DTR3D · ScanNet v2FPS: 23.7 -> 18.2Hurt

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