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
- Linked via arxiv authorErich Liang →
InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics
- Linked via arxiv authorCaleb Kha-Uong →
InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics
- Linked via arxiv authorChinmaya Saran →
InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics
- Linked via arxiv authorSreemanti Dey →
InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics
- Linked via arxiv authorDavid W. Liu →
InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics
- Linked via arxiv authorJunhan Ouyang →
InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics
- Linked via arxiv authorBenjamin Zhou →
InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics
- Linked via arxiv authorJia Deng →
InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics