MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection
Monocular temporal 3D detection aims to detect objects in 3D, given a monocular video. Query-based 3D detectors unify detection and cross-view association, but their learnable queries fit the spatial distribution of the training data (e.g., field-of-view). We show that this issue is especially severe when these models are applied to monocular video, hindering generalization to unseen datasets and environments. To address this limitation, we introduce MAGneT-3D, the first method for domain-generalized monocular temporal 3D object detection. Instead of relying on static learnable queries, we pro
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Mohamed Kotb →
“MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection”
- LinkedLinked via arxiv author · 85%Johannes Meier →
“MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection”
- LinkedLinked via arxiv author · 85%Christoph Reich →
“MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection”
- LinkedLinked via arxiv author · 85%Oussema Dhaouadi →
“MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection”
- LinkedLinked via arxiv author · 85%Luis Denninger →
“MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection”
- LinkedLinked via arxiv author · 85%Daniel Cremers →
“MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection”