AI Paper Atlas

Research map / Point clouds / Segmentation and detection

A Realism Metric for Generated LiDAR Point Clouds

Larissa T. Triess, Christoph B. Rist, David Peter, J. Marius Zöllner

IJCV 2022 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 15 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 gradient-reversal adversaries (lambda=0.3) to the classifier (ablation)realism metric · metric calibrationclassifier accuracy vs adversary accuracy: 93 classifier vs 50 adversary (chance level)Improved
raise adversarial factor lambda too high (ablation)realism metric · metric calibrationclassifier accuracyHurt
use one adversary per category instead of a single common adversary (ablation)realism metric · feature embedding t-SNEfeature clusteringImproved
add adversary to classifier (ablation)realism metric · unseen PandaSetembeddingImproved
per-category adversaries instead of Real-only adversary (ablation)realism metric · Misc categoryfeature mixingImproved
up-sample with L1-CNN instead of nearest neighborKITTI up-sampling · KITTI val segmentationmean IoU: 41.5 -> 49.1Improved
up-sample with GAN instead of L1-CNNKITTI up-sampling · KITTI val segmentationmean IoU: 49.1 -> 47.2Hurt
train on original high-resolution KITTI instead of up-sampledDarkNet21 · KITTI val segmentationmean IoU: 49.1 -> 51.4Improved
use L2-CNN or GAN generated data for dynamic classesDarkNet21 · KITTI val segmentationperson IoU: 10.9 -> 16.5Mixed
rank up-sampling by realism score rather than reconstruction errorrealism metric · KITTI 4x up-samplingrankingImproved

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