AI Paper Atlas

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

WayPOP: A Panoramic Open-Set Panoptic Tracking Benchmark

Rohit Mohan, Maximilian Luz, Swarnava Chowdhury, Yao Lu, Florian Drews, Thomas Nürnberg, Yakov Miron, Federico Tombari, Stefano Gasperini, Abhinav Valada

NeurIPS 2026 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces WayPOP, a panoramic open-set panoptic tracking benchmark for autonomous driving that evaluates detecting, segmenting, and tracking out-of-distribution objects across time and multiple camera views.

Problem

Existing panoptic tracking benchmarks assume a fixed semantic taxonomy and so cannot test whether panoramic multi-camera driving systems detect, segment, and track out-of-distribution objects across time and viewpoints.

Approach

A benchmark designed for open-set panoramic panoptic tracking, so that OOD objects must be detected, segmented and tracked across time and multiple cameras rather than only classified within a closed taxonomy.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use open-set methods instead of open-vocabulary Mask2Former-style methods for unknown objectspanoptic segmentation baselines · WayPOP-v1 VI-OSPSUnknown PQ: FC-CLIP 0.2 -> PoDS 34.6Improved
use caption-supervised ODISEopen-vocabulary segmentation · WayPOP-v1 VI-OSPSUnknown PQ: 30.9 vs <=1.0 for other OV methodsImproved
use appearance-based trackers (MASA, DEVA) instead of motion-based BoT-SORTFV-OSPT · WayPOP-v1Unknown AQ: PoDS: 14.8 -> 20.7 (MASA)Improved
extend from frontal-view to multi-view trackingPoDS + DEVA · WayPOP-v1Unknown STQ vs wSTQ: 30.0 (FV) vs 37.1 (MV) different metricsMixed
use ground-truth masks (oracle) with DEVAMV-OSPT · WayPOP-v1Known wAQ: 11.4 -> 43.5Improved
change ODISE unknown prompt from 'unknown object' to full vocabulary (ablation)ODISE · WayPOP-v1Unknown PQ: 7.7 -> 30.9Improved
change ODISE unknown prompt (ablation)ODISE · WayPOP-v1Known PQ: 24.0 to 24.4No clear effect
add lighting adaptation, occlusion handling and harmonization to insertion pipeline (ablation)benchmark construction · WayPOP-v1 dev, RbAUnknown PQ: 38.0 -> 29.9Hurt
add lighting adaptation, occlusion handling and harmonization (ablation)benchmark construction · WayPOP-v1FID: 14.762 -> 9.745Improved
use Objaverse-XL assets instead of Objaverse v1.0open-set methods · WayPOP VI-OSPSUnknown PQ: PoDS 34.6 -> 31.1No clear effect
use Objaverse-XL assets instead of v1.0ODISE · WayPOP VI-OSPSUnknown PQ: 30.9 -> 23.6Hurt

Experimental setup

Benchmarks: WayPOP

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