Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
chenweikai authored Jun 16, 2022
1 parent 865e4a6 commit 036da19
Showing 1 changed file with 20 additions and 4 deletions.
24 changes: 20 additions & 4 deletions data_generation/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ After compilation, binaries named `gen_3psdf_samples` and `batch_generate` will

(1) `gen_3psdf_samples`: the binary generates 3PSDF sampling points using octree-based sampling.

Simply run `./gen_3psdf_samples` under the `build` folder will activate a demo setting that reconstructs `soldier_fight.obj` (a 3D character with both closed and open surfaces) under `/data` folder and saves (a) the generated 3PSDF samples for training (the`.sdf`file), (b) the mesh reconstructed from the computed 3PSDF field for debugging purpose (the`.obj`file), and (c) the sampling point positions for debugging purpose (the`.ply`file) to the `/output` folder.
Simply run `./gen_3psdf_samples` under the `build` folder will activate a demo setting that reconstructs `soldier_fight.obj` (a 3D character with both closed and open surfaces) under `/data` folder and saves (a) the generated 3PSDF samples for training (the`.sdf`file), (b) the mesh reconstructed from the computed 3PSDF field for debug purpose (the`.obj`file), and (c) the sampling point positions for debug purpose (the`.ply`file) to the `/output` folder.

To customize the usage of the program:

Expand All @@ -45,11 +45,11 @@ To customize the usage of the program:

`octree_depth`: the depth of the octree that is used to generate sampling points. The larger the depth, the more accurate is the 3PSDF reconstruction.

`flag_writeSDF`: whether to generate `.sdf` file (currenlty can be viewed in any text editor for illustration purpose, you are welcomed to customized it into a binary format for acceleration) that encodes the raw training samples for 3PSDF learning. By default, it is set to 1 to activate sdf generation; it is disabled when set to 0.
`flag_writeSDF`: flag of whether to generate `.sdf` file (currenlty can be viewed in any text editor for illustration purpose, you are welcomed to customized it into a binary format for acceleration) that encodes the raw data samples for 3PSDF learning. By default, it is set to 1 to activate sdf generation; it is disabled when set to 0.

`flag_recon_3PSDF`: whether to reconstruct the generated 3PSDF field to a mesh for debug purpose. By default, it is set to 1 to activate the generation; it is disabled when set to 0.
`flag_recon_3PSDF`: flag of whether to reconstruct the generated 3PSDF field to a mesh for debug purpose. By default, it is set to 1 to activate the generation; it is disabled when set to 0.

`flag_writePLY`: whether to generate `.ply` file that encodes the sampling points used in the `.sdf' training data. It is used for debug and visualization purpose. By default, it is set to 1 to activate the generation; it is disabled when set to 0.
`flag_writePLY`: flag of whether to generate `.ply` file that encodes the sampling points used in the `.sdf' training data. It is used for debug and visualization purpose. By default, it is set to 1 to activate the generation; it is disabled when set to 0.


(2) `batch_generate`: the binary that generates 3PSDF sampling points in batch.
Expand All @@ -62,6 +62,22 @@ To customize the usage of the program:
flag_writeSDF [default=0] flag_writeOBJ [default=1] flag_writePLY [default=1] [todo_list.txt (optional)]"
```

`inDir`: repository containing input meshes that are ready to be batch processed.

`outSDFDir`: repository for outputing the generated `.sdf` files (raw data samples for 3PSDF training).

`outObjDir`: repository for outputing the reconstructed `.obj` files (reconstructed meshed from the output 3PSDF field).

`outPlyDir`: repository for outputing the sampling points encoded in `.ply` format.

`octree_depth`: the depth of the octree that is used to generate sampling points. The larger the depth, the more accurate is the 3PSDF reconstruction.

`flag_writeSDF`: flag of whether to generate `.sdf` file (currenlty can be viewed in any text editor for illustration purpose, you are welcomed to customized it into a binary format for acceleration) that encodes the raw data samples for 3PSDF learning. By default, it is set to 1 to activate sdf generation; it is disabled when set to 0.

`flag_recon_3PSDF`: flag of whether to reconstruct the generated 3PSDF field to a mesh for debug purpose. By default, it is set to 1 to activate the generation; it is disabled when set to 0.

`flag_writePLY`: flag of whether to generate `.ply` file that encodes the sampling points used in the `.sdf' training data. It is used for debug and visualization purpose. By default, it is set to 1 to activate the generation; it is disabled when set to 0.


## Contacts

Expand Down

0 comments on commit 036da19

Please sign in to comment.