This is the Linux app named VGGSfM whose latest release can be downloaded as vggsfmsourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named VGGSfM with OnWorks for free.
이 앱을 실행하려면 다음 지침을 따르세요.
- 1. 이 애플리케이션을 PC에 다운로드했습니다.
- 2. 파일 관리자 https://www.onworks.net/myfiles.php?username=XXXXX에 원하는 사용자 이름을 입력합니다.
- 3. 이러한 파일 관리자에서 이 응용 프로그램을 업로드합니다.
- 4. 이 웹사이트에서 OnWorks Linux 온라인 또는 Windows 온라인 에뮬레이터 또는 MACOS 온라인 에뮬레이터를 시작합니다.
- 5. 방금 시작한 OnWorks Linux OS에서 원하는 사용자 이름으로 파일 관리자 https://www.onworks.net/myfiles.php?username=XXXXX로 이동합니다.
- 6. 응용 프로그램을 다운로드하여 설치하고 실행합니다.
스크린 샷
Ad
VGGSfM
기술
VGGSfM is an advanced structure-from-motion (SfM) framework jointly developed by Meta AI Research (GenAI) and the University of Oxford’s Visual Geometry Group (VGG). It reconstructs 3D geometry, dense depth, and camera poses directly from unordered or sequential images and videos. The system combines learned feature matching and geometric optimization to generate high-quality camera calibrations, sparse/dense point clouds, and depth maps in standard COLMAP format. Version 2.0 adds support for dynamic scene handling, dense point cloud export, video-based reconstruction (1000+ frames), and integration with Gaussian Splatting pipelines. It leverages tools like PyCOLMAP, poselib, LightGlue, and PyTorch3D for feature matching, pose estimation, and visualization. With minimal configuration, users can process single scenes or full video sequences, apply motion masks to exclude moving objects, and train neural radiance or splatting models directly from reconstructed outputs.
기능
- End-to-end 3D reconstruction from images or videos with automatic camera pose estimation
- Outputs in standard COLMAP format compatible with NeRF and Gaussian Splatting pipelines
- Supports over 1000 sequential frames with sliding-window video processing
- Handles dynamic/moving scenes via optional binary masks
- Exports dense point clouds and dense depth maps (beta)
- Easily integrates with gsplat for Gaussian Splat training
- Interactive visualization using Gradio or Visdom
- Pretrained model auto-downloaded from Hugging Face or Google Drive
프로그래밍 언어
파이썬, 유닉스 셸
카테고리
This is an application that can also be fetched from https://sourceforge.net/projects/vggsfm.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
