AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Fast Point R-CNN

Yilun Chen, Shu Liu, Xiaoyong Shen, Jiaya Jia

ICCV 2019 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 412 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 3D convolutions in lower layers (ablation)VoxelRPN baseline · KITTI val3D AP0.7 moderate: 73.8 -> 74.7Improved
add higher resolution voxel input (ablation)VoxelRPN · KITTI val3D AP0.7 moderate: 74.7 -> 75.34Improved
add MIXUP augmentation (ablation)VoxelRPN · KITTI val3D AP0.7 moderate: 75.34 -> 75.82Improved
use 4 anchor angles instead of 2 (ablation)VoxelRPN · KITTI val3D AP0.7 moderate: 75.82 -> 76.64Improved
add RefinerNet second stage (ablation)VoxelRPN · KITTI val3D AP0.7 moderate: 76.64 -> 79.0Improved
add RefinerNet second stage (ablation)VoxelRPN · KITTI val3D AP0.8 moderate: 42.6 -> 52.95Improved
add RefinerNet second stage for distant objects (30-50 m) (ablation)VoxelRPN · KITTI val3D AP0.7 moderate: 51.99 -> 58.41Improved
add RefinerNet second stage for BEV at loose IoU (ablation)VoxelRPN · KITTI valBEV AP0.7 moderate (0-30 m): 90.22 -> 90.25No clear effect
fuse coordinate and convolution features with attention instead of concatenation (ablation)RefinerNet · KITTI val3D AP0.7 moderate: 78.38 -> 79.00Improved
add convolution feature to coordinate feature (concatenation) (ablation)RefinerNet · KITTI val3D AP0.7 moderate: 77.82 -> 78.38Improved
use canonized corner loss instead of naive 7-parameter regression (ablation)RefinerNet · KITTI val3D AP0.7 moderate: 78.45 -> 79Improved
use RefinerNet instead of rotated RoI Align refinement (ablation)Fast Point R-CNN · KITTI val3D AP0.7 moderate: 77.39 -> 79.00Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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