ActMVS: Active Scene Reconstruction with Monocular Multi-View Stereo
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913177700139008 |
|---|---|
| author | Pu, Guo Han, Yixuan Lian, Zhouhui |
| author_facet | Pu, Guo Han, Yixuan Lian, Zhouhui |
| contents | Active scene reconstruction enables robots/UAVs to autonomously plan trajectories and reconstruct environments without costly manual data acquisition. Unlike passive methods, active reconstruction requires real-time construction of high-confidence occupancy maps for collision-free navigation. Existing approaches rely on depth sensors for occupancy map updates, increasing platform cost and weight. To advance spatial intelligence, we aim for a vision-only monocular solution. However, current monocular scene reconstruction methods operate offline and fail to deliver globally consistent dense depth at the frame rates required for robots/UAVs navigation. To bridge this gap, we introduce ActMVS, the first framework for monocular active reconstruction. Our framework integrates a view factor graph construction for informed Multi-View Stereo depth prediction, along with a global depth optimization, to enable the online generation of high-quality, globally consistent dense depth maps. This enables monocular robots/UAVs to maintain reliable occupancy maps for safe trajectory planning during reconstruction. Experiments on Replica datasets demonstrate performance competitive with RGB-D methods. Our code and data are available at https://github.com/TrickyGo/ActMVS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01367 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ActMVS: Active Scene Reconstruction with Monocular Multi-View Stereo Pu, Guo Han, Yixuan Lian, Zhouhui Robotics Computer Vision and Pattern Recognition Active scene reconstruction enables robots/UAVs to autonomously plan trajectories and reconstruct environments without costly manual data acquisition. Unlike passive methods, active reconstruction requires real-time construction of high-confidence occupancy maps for collision-free navigation. Existing approaches rely on depth sensors for occupancy map updates, increasing platform cost and weight. To advance spatial intelligence, we aim for a vision-only monocular solution. However, current monocular scene reconstruction methods operate offline and fail to deliver globally consistent dense depth at the frame rates required for robots/UAVs navigation. To bridge this gap, we introduce ActMVS, the first framework for monocular active reconstruction. Our framework integrates a view factor graph construction for informed Multi-View Stereo depth prediction, along with a global depth optimization, to enable the online generation of high-quality, globally consistent dense depth maps. This enables monocular robots/UAVs to maintain reliable occupancy maps for safe trajectory planning during reconstruction. Experiments on Replica datasets demonstrate performance competitive with RGB-D methods. Our code and data are available at https://github.com/TrickyGo/ActMVS. |
| title | ActMVS: Active Scene Reconstruction with Monocular Multi-View Stereo |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2606.01367 |