tink/nerfstudio
4
0
Fork 0
mirror of https://github.com/nerfstudio-project/nerfstudio.git synced 2026-11-10 18:17:31 +08:00
Code

Hloc fix for image_ids (camera per image) (#3081)

Browse Source 
* changed run_hloc args to fill image_ids (added image_list and changed camera_mode to PER_IMAGE)

* added parameter same_camera on ns-process-data for multifocal cases in hloc. Also updated colmap_to_json to detect if there is one or several cameras per frame while keeping the camera type specifications

* ruff-formatted changes in colmap_utils.py

* use_single_camera_mode update args, including colmap_utils and hloc_utils

* changed multicamera warning's print to CONSOLE.print

* fix path typo console print

* rewritten use-single-camera-mode comment in ns-process-data

* (fix) inverted bool for colmap_utils

* change im_id to im_data.camera_id

---------

Co-authored-by: Jianbo Ye <jianboye@amazon.com>
This commit is contained in:
dberga 2024-04-24 18:43:45 +02:00 committed by GitHub
parent d9b022b25f
commit db93476b6a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 31 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
nerfstudio/process_data/colmap_converter_to_nerfstudio_dataset.py
View File

@ -101,6 +101,9 @@ class ColmapConverterToNerfstudioDataset(BaseConverterToNerfstudioDataset):
"""If --use-sfm-depth and this flag is True, also export debug images showing Sf overlaid upon input images."""
same_dimensions: bool = True
"""Whether to assume all images are same dimensions and so to use fast downscaling with no autorotation."""
use_single_camera_mode: bool = True
"""Whether to assume all images taken with the same camera characteristics, set to False for multiple cameras in colmap (only works with hloc sfm_tool).
"""
@staticmethod
def default_colmap_path() -> Path:
@ -136,6 +139,7 @@ class ColmapConverterToNerfstudioDataset(BaseConverterToNerfstudioDataset):
image_id_to_depth_path=image_id_to_depth_path,
camera_mask_path=camera_mask_path,
image_rename_map=image_rename_map,
use_single_camera_mode=self.use_single_camera_mode,
)
summary_log.append(f"Colmap matched {num_matched_frames} images")
summary_log.append(colmap_utils.get_matching_summary(num_frames, num_matched_frames))
@ -194,6 +198,10 @@ class ColmapConverterToNerfstudioDataset(BaseConverterToNerfstudioDataset):
if self.refine_pixsfm:
assert sfm_tool == "hloc", "refine_pixsfm only works with sfm_tool hloc"
# check that sfm_tool is hloc if using use_single_camera_mode
if not self.use_single_camera_mode:
assert sfm_tool == "hloc", "not_use_single_camera_mode only works with sfm_tool hloc"
# set the image_dir if didn't copy
if self.skip_image_processing:
image_dir = self.data
@ -228,6 +236,7 @@ class ColmapConverterToNerfstudioDataset(BaseConverterToNerfstudioDataset):
feature_type=feature_type,
matcher_type=matcher_type,
refine_pixsfm=self.refine_pixsfm,
use_single_camera_mode=self.use_single_camera_mode,
)
else:
raise RuntimeError("Invalid combination of sfm_tool, feature_type, and matcher_type, " "exiting")

15
nerfstudio/process_data/colmap_utils.py
View File

@ -395,6 +395,7 @@ def colmap_to_json(
image_rename_map: Optional[Dict[str, str]] = None,
ply_filename="sparse_pc.ply",
keep_original_world_coordinate: bool = False,
use_single_camera_mode: bool = True,
) -> int:
"""Converts COLMAP's cameras.bin and images.bin to a JSON file.
@ -418,6 +419,13 @@ def colmap_to_json(
# im_id_to_image = recon.images
cam_id_to_camera = read_cameras_binary(recon_dir / "cameras.bin")
im_id_to_image = read_images_binary(recon_dir / "images.bin")
if set(cam_id_to_camera.keys()) != {1}:
CONSOLE.print(f"[bold yellow]Warning: More than one camera is found in {recon_dir}")
print(cam_id_to_camera)
use_single_camera_mode = False # update bool: one camera per frame
out = {} # out = {"camera_model": parse_colmap_camera_params(cam_id_to_camera[1])["camera_model"]}
else: # one camera for all frames
out = parse_colmap_camera_params(cam_id_to_camera[1])
frames = []
for im_id, im_data in im_id_to_image.items():
@ -455,11 +463,12 @@ def colmap_to_json(
if image_id_to_depth_path is not None:
depth_path = image_id_to_depth_path[im_id]
frame["depth_file_path"] = str(depth_path.relative_to(depth_path.parent.parent))
if not use_single_camera_mode: # add the camera parameters for this frame
frame.update(parse_colmap_camera_params(cam_id_to_camera[im_data.camera_id]))
frames.append(frame)
if set(cam_id_to_camera.keys()) != {1}:
raise RuntimeError("Only single camera shared for all images is supported.")
out = parse_colmap_camera_params(cam_id_to_camera[1])
out["frames"] = frames
applied_transform = None

12
nerfstudio/process_data/hloc_utils.py
View File

@ -71,6 +71,7 @@ def run_hloc(
] = "superglue",
num_matched: int = 50,
refine_pixsfm: bool = False,
use_single_camera_mode: bool = True,
) -> None:
"""Runs hloc on the images.
@ -85,6 +86,7 @@ def run_hloc(
matcher_type: Type of feature matcher to use.
num_matched: Number of image pairs for loc.
refine_pixsfm: If True, refine the reconstruction using pixel-perfect-sfm.
use_single_camera_mode: If True, uses one camera for all frames. Otherwise uses one camera per frame.
"""
if not _HAS_HLOC:
CONSOLE.print(
@ -119,6 +121,12 @@ def run_hloc(
match_features.main(matcher_conf, sfm_pairs, features=features, matches=matches) # type: ignore
image_options = pycolmap.ImageReaderOptions(camera_model=camera_model.value) # type: ignore
if use_single_camera_mode: # one camera per all frames
camera_mode = pycolmap.CameraMode.SINGLE # type: ignore
else: # one camera per frame
camera_mode = pycolmap.CameraMode.PER_IMAGE # type: ignore
if refine_pixsfm:
sfm = PixSfM( # type: ignore
conf={
@ -134,7 +142,7 @@ def run_hloc(
features,
matches,
image_list=references,
camera_mode=pycolmap.CameraMode.SINGLE, # type: ignore
camera_mode=camera_mode, # type: ignore
image_options=image_options,
verbose=verbose,
)
@ -147,7 +155,7 @@ def run_hloc(
sfm_pairs,
features,
matches,
camera_mode=pycolmap.CameraMode.SINGLE, # type: ignore
camera_mode=camera_mode, # type: ignore
image_options=image_options,
verbose=verbose,
)