AI Paper Atlas

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

Stereo Neural Vernier Caliper

Shichao Li, Zechun Liu, Zhiqiang Shen, Kwang-Ting Cheng

AAAI 2022 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 6 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
Refine RTS-3D proposals with the Vernier scale networkRTS-3D · KITTI val, ModerateAP3D: 41.61 -> 52.92Improved
Refine IDA-3D proposals with the Vernier scale networkIDA-3D · KITTI val, ModerateAP3D: 36.79 -> 48.89Improved
Use multiple object parts (K=9) instead of center-only prediction (K=1) (ablation)RTS-3D + Vernier scale · KITTI val, ModerateAP3D: 47.22 -> 52.92Improved
Use multiple object parts (K=9) instead of center-only prediction (K=1) (ablation)RTS-3D + Vernier scale · KITTI val, HardAP3D: 43.73 -> 45.82Improved
Use a finer voxel grid (192, 32, 128) instead of (48, 16, 32) (ablation)RTS-3D + Vernier scale · KITTI val, ModerateAP3D: 44.31 -> 52.92Improved
Use a finer voxel grid (192, 32, 128) instead of an extremely coarse grid (24, 16, 16) (ablation)RTS-3D + Vernier scale · KITTI val, ModerateAP3D: 27.84 -> 52.92Improved
Add high-resolution instance-level refinement to coarse scene-level stereo detectionSNVC · KITTI val and testAP3D: KITTI val Moderate: 54.27 -> 63.75; KITTI test Moderate: 54.22 -> 61.34Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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