AI Paper Atlas

Research map / 3D vision / 3D generation

TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception

Quinlan Sykora, Sourav Biswas, Christopher Diehl, Andrew Cunningham, Thomas Gilles, Raquel Urtasun

ECCV 2026 · 3D vision › 3D generation · approach: Vision-based 3D occupancy prediction · 0 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 unsupervised pre-training (ablation)TriO · LRR (200m+)mAP: 41.0 -> 42.6Improved
add RADAR as input modality (ablation)TriO · LRR (200m+)mAP: 34.5 -> 42.6Improved
add camera input (ablation)TriO · LRR (200m+)mAP: 42.2 -> 42.6No clear effect
add camera input (ablation)TriO · LRR (all ranges)EPE: 2.68 -> 2.86Hurt
add RADAR Doppler flow loss (ablation)TriO · LRR (all ranges)EPE: 4.35 -> 2.86Improved
add RADAR Doppler flow loss (ablation)TriO · LRR (200m+)EPE: 6.02 -> 4.01Improved
use soft probabilistic labels instead of hard thresholded labels (CSL Soft vs Hard)TriO · STU semantic occupancyAP: 76.1 -> 81.6Improved
add camera-based image supervision to LiDAR-only model under CSL labels (TriO vs DiO)TriO · STU semantic occupancymIoU: 49.8 -> 54.9Improved
fuse image and LiDAR pseudo-labels (CSL vs image-only ISL)pseudo-labels · STU pseudo-label segmentationmIoU: 38.6 -> 44.6Improved
add oracle class prompts to OWLv2 + SAMOWLv2 + SAM · STU pseudo-label segmentationmIoU: 20.2 -> 28.6Improved
pre-train with RADAR in TriO vs DIO on flow in AV2TriO · AV2 fine-tuned occupancyEPE: 1.43 -> 1.97Hurt

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