videocameraposemegasammapper

September 8, 2026 · View on GitHub

Extract camera poses by leveraging MegaSaM and MoGe-2.

利用 MegaSaM 和 MoGe-2 提取相机位姿。

Type 算子类型: mapper

Tags 标签: gpu, video

🔧 Parameter Configuration 参数配置

name 参数名type 类型default 默认值desc 说明
tag_field_name<class 'str'>'video_camera_pose_tags'The field name to store the tags. It's "video_camera_pose_tags" in default.
frame_field<class 'str'>'video_frames'The field name where the video frames are stored.
camera_calibration_field<class 'str'>'camera_calibration'The field name where the camera calibration info is stored.
max_frames<class 'int'>1000Maximum number of frames to save.
droid_buffer<class 'int'>1024DROID SLAM pre-allocated frame buffer size. Controls GPU memory usage — each buffer slot pre-allocates correlation volumes on GPU. Default 1024, sufficient for clips up to ~100 frames. Reduce for shorter clips to save VRAM, increase for longer videos.
save_dir<class 'str'>NoneDirectory to save large numpy arrays (depth, cam_c2w) as .npy files instead of storing them inline. When set, tag_dict stores file paths (strings) instead of numpy arrays, which avoids memory limit.
use_prepare_env<class 'bool'>FalseWhether to prepare the environment.
args``extra args
kwargs``extra args