InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics
Camera intrinsics are vital for recovering 3D structure from 2D video. However, most 3D algorithms assume fixed intrinsics throughout a video, an assumption that often fails for real-world in-the-wild videos. Consequently, estimating per-frame intrinsics from RGB images is critical for making 3D methods robust to videos with dynamic intrinsics. InFlux previously advanced this research direction by establishing the first real-world benchmark with per-frame ground truth intrinsics for dynamic intrinsics videos. Nevertheless, existing methods remain inaccurate due to two obstacles: (i) training d
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.
- PossiblePossibly related (embedding) · 51%Into the Omniverse: Three Workflows for Improving Vision AI Agent Accuracy With Synthetic Data and Fine-Tuning →
- PossiblePossibly related (embedding) · 48%Showcase: geolocating a dashcam video without GPS, only from the footage [P] →
- LinkedLinked via arxiv author · 85%Erich Liang →
“InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics”
- LinkedLinked via arxiv author · 85%Caleb Kha-Uong →
“InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics”
- LinkedLinked via arxiv author · 85%Chinmaya Saran →
“InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics”
- LinkedLinked via arxiv author · 85%Sreemanti Dey →
“InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics”
- LinkedLinked via arxiv author · 85%David W. Liu →
“InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics”
- LinkedLinked via arxiv author · 85%Junhan Ouyang →
“InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics”