Augmenting TV Shows via Uncalibrated Camera Small Motion Tracking in Dynamic Scene
Yizhen Lao, Jie Yang, Xinying Wang, Jianxin Lin, Yu Cao, Shien Song
Abstract
To augment the TV show in post-production, we propose a novel solution to uncalibrated camera small motion tracking in a dynamic scene that simultaneously reconstructs the sparse 3D scene and computes camera poses and focal lengths of each frame. The critical elements of our approach are a robust image feature tracking strategy in dynamic scenes followed by automatic local-window frames slicing, local and global bundle adjustment optimization initialized by a homography-based uncalibrated relative rotation solver. The proposed method allows us to add the virtual objects (elements) into the reconstructed 3D scene, then composite them back into the original shot while perfectly matched perspective and appear seamless.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Related papers
- Back on Track: Bundle Adjustment for Dynamic Scene ReconstructionWeirong Chen, Ganlin Zhang, Felix Wimbauer, Rui Wang et al.ICCV 2025 · 1 citation
- ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular VideosShi Chen, Erik Sandström, Sandro Lombardi, Siyuan Li et al.NeurIPS 2025 · 1 citation
- RoMo: Robust Motion Segmentation Improves Structure from MotionLily Goli, Sara Sabour, Mark J. Matthews, Marcus A. Brubaker et al.ICCV 2025 · 2 citations
- ShowMak3r: Compositional TV Show ReconstructionSangmin Kim, Seunguk Do, Jaesik ParkCVPR 2025
- 4D Gaussian Splatting SLAMYanyan Li, Youxu Fang, Zunjie Zhu, Kunyi Li et al.ICCV 2025 · 3 citations
