AI Paper Atlas

Research map / Detection and segmentation / CNN features

Lidar Panoptic Segmentation in an Open World

Anirudh Srinivasan Chakravarthy, Meghana Reddy Ganesina, Peiyun Hu, Laura Leal-Taixé, Shu Kong, Deva Ramanan, Aljoša Ošep

IJCV 2024 · Detection and segmentation › CNN features · approach: Unified panoptic segmentation · 7 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
use class-agnostic hierarchical grouping instead of class-specific (ablation)OWL · SemanticKITTI val (closed world)Prec Th: 79.7 -> 79.9Improved
add holistic second-stage objectness classifier (ablation)OWL · SemanticKITTI val (closed world)PQ: 58.7 -> 58.8Improved
add regression loss for objectness (ablation)OWL · SemanticKITTI val (closed world)PQ: 58.8 -> 58.9Improved
add semantic majority vote within each segment (ablation)OWL · SemanticKITTI val (closed world)PQ: 58.9 -> 59.0Improved
replace learned semantic classifier with GT semantic mapOWL · SemanticKITTI val (closed world)PQ: 59.0 -> 98.3Improved
use perfect objectness oracle scoresOWL · SemanticKITTI val (closed world)PQ: 59.0 -> 59.2Improved
use OWL grouping over 4D-PLS inference4D-PLS · SemanticKITTI val (closed world)PQ: 56.5 -> 58.7Improved
use OWL instead of 4D-PLS for known classes4D-PLS · KITTI360 (cross-dataset), Vocabulary 1 knownPQ: 56.1 -> 59.4Improved
use OWL instead of 4D-PLS for unknown instances4D-PLS · KITTI360 (cross-dataset), Vocabulary 1 unknownRecall: 2.0 -> 45.1Improved
lower center-objectness threshold for other-class points at inference (ablation)4D-PLS · KITTI360 (cross-dataset), Vocabulary 1 unknownRecall: 2.0 -> 6.0Improved
use separate learned grouping for thing classes and hierarchical segmentation for other (ablation)OWL · KITTI360 (cross-dataset), Vocabulary 1 unknownUQ: 36.3 -> 36.6No clear effect
group rare classes into catch-all other (Vocabulary 1 vs 2)OWL · KITTI360 (cross-dataset)PQ: 53.4 -> 59.4Improved

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