ResearcharXivNEW

VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion

Pataki 2026-07-29
Zador PatakiPaul-Edouard SarlinMarc Pollefeys

Accurately recovering the camera's calibration and metric poses for any unconstrained video would unlock large-scale training data for navigation and scene understanding. The dominant approaches to this problem are severely limited: Simultaneous Localization and Mapping (SLAM) is sensitive to initialization and transient failures due to its causal, incremental nature; it is often over-optimized fo

Read on arXiv
Data aggregated and editorially reviewed by TrendMing.

Key Contributions

  • Accurately recovering the camera's calibration and metric poses for any unconstrained video would unlock large-scale training data for navigation and scene understanding.
  • The dominant approaches to this problem are severely limited: Simultaneous Localization and Mapping (SLAM) is sensitive to initialization and transient failures due to its causal, incremental nature; it is often over-optimized fo

Research Themes

AIResearch