AI Paper Atlas

Research map / Point clouds / Segmentation and detection

CT3D++: Improving 3D Object Detection with Keypoint-Induced Channel-wise Transformer

Xian-Sheng Hua, Sijia Cai, Na Zhao, Bing Deng, Qiao Liang, Min-Jian Zhao, Jieping Ye

IJCV 2025 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 10 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 extended channel-wise re-weighting decoder (ablation)CT3D++ · Waymo 20% Vehicle L2AP: 65.2 -> 68.9Improved
add extended channel-wise re-weighting decoder (ablation)CT3D++ · Waymo 20% Cyclist L2AP: 53.5 -> 61.1Improved
replace channel-wise re-weighting alone with standard cross-attention (ablation)decoder · Waymo 20% Vehicle L2AP: 65.2 -> 65.3No clear effect
add geometric raw-point embedding to semantic-only embedding (ablation)CT3D++ · Waymo 20% Vehicle L2AP: 64.1 -> 68.9Improved
add BEV semantic features to geometric-only embedding (ablation)CT3D++ · Waymo 20% Cyclist L2AP: 60.5 -> 61.1Improved
add voxel features from RPN middle layers (ablation)CT3D++ · Waymo 20% Vehicle L2AP: 68.9 -> 69.0No clear effect
use PBC instead of self-attention (ablation)CT3D++ · Waymo 20% Vehicle L2AP: 64.5 -> 68.9Improved
use PBC instead of MLP (ablation)CT3D++ · Waymo 20% Vehicle L2AP: 66.4 -> 68.9Improved
use PBC instead of self-attention at 32 epochs (ablation)CT3D++ · Waymo 20% Vehicle L1AP: 72.9 -> 78.5Improved
decode on raw points instead of key points (ablation)CT3D++ · Waymo 20% Vehicle L2AP: 68.6 -> 68.9Improved
use category-based instead of object-based raw point sampling (ablation)CT3D++ · Waymo 20% Vehicle L2AP: 69.0 -> 68.9No clear effect
upgrade CT3D to CT3D++ with PointPillar RPN (ablation)RPN refinement · Waymo 20% Vehicle L2AP: 62.6 -> 64.8Improved

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