Dense point cloud in the header image

[zdwww]

Hi! While your work and dataset are truly inspiring, I'm wondering how can we obtain the very dense point cloud (illustrated in the header image, the paper's figure1 or the video you posted) from either sparse reconstruction or dense registration in COLMAP. Either the sparse/dense raw data you made available is far more sparse than in the figure.

I will be more than appreciated if you could illustrate the process since a vivid and expressive point cloud background can be truly helpful in all ways.

Thank you!

[zhifanzhu]

Hi!👋 Thanks for the interest.

To get the dense point cloud, you'll need to download the sparse COLMAP data link, then run COLMAP's image_undistorter, patch_match_stereo and stereo_fusion.

# Place the epic-kitchens frames in $DATASET_PATH/images, 
# i.e. $DATASET_PATH/images/{frame_0000000001.jpg, ...}, 
# image resolution should be 456x256.

$ mkdir $DATASET_PATH/dense

$ colmap image_undistorter \
    --image_path $DATASET_PATH/images \
    --input_path $DATASET_PATH/sparse/0 \
    --output_path $DATASET_PATH/dense \
    --output_type COLMAP \
    --max_image_size 2000

$ colmap patch_match_stereo \
    --workspace_path $DATASET_PATH/dense \
    --workspace_format COLMAP \
    --PatchMatchStereo.geom_consistency true

$ colmap stereo_fusion \
    --workspace_path $DATASET_PATH/dense \
    --workspace_format COLMAP \
    --input_type geometric \
    --output_path $DATASET_PATH/dense/fused.ply

The patch_match_stereo step can take up to ~20hrs for one video.

Explanation of the commands can be found in COLMAP's faq and cli.

[zdwww]

Thank you so much for your illustration! This's very helpful.

[JudyYe]

Hi team,

Great work! Congratulations!

Could you please explain the relation between the colmap commands above and the raw COLMAP format from EPIC-FIELDS website? More specifically, the two links on the website the output or the input to the 3 colmap commands? Thanks!

The dense registered frames in raw COLMAP format can be found at: here (133G). The sparse frames including raw COLMAP database can be found at: here (91.6G).

[dimadamen]

As answered elsewhere