nvs2colmap 0.3.2__tar.gz → 0.4.0__tar.gz

{nvs2colmap-0.3.2 → nvs2colmap-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nvs2colmap
-Version: 0.3.2
+Version: 0.4.0
 Summary: Utilities for converting novel view synthesis datasets to COLMAP format.
 Author-email: Howard Yin <yindaheng98@gmail.com>
 Maintainer-email: Howard Yin <yindaheng98@gmail.com>
@@ -31,6 +31,8 @@ Dynamic: license-file
 
 Utilities for converting novel view synthesis datasets to COLMAP format.
 
+**These scenes are prepared for [InstantSplat](https://github.com/yindaheng98/InstantSplat). The default commands write known-pose `sparse/0` text models and do not call COLMAP. `--use-colmap` runs feature extraction, matching, triangulation, and mapping, then stops at `distorted/sparse/0`. InstantSplat undistorts images and masks together with `image_undistorter` and `mask_undistorter`. This repository does not undistort, because `image_undistorter` alone leaves masks untouched.**
+
 ## Supported Formats
 
 - **Neural 3D Video Dataset**: scenes with `poses_bounds.npy` and one `mp4`
@@ -65,11 +67,13 @@ pip install numpy plyfile torch
 ```
 
 For Neural 3D Video scenes, the command also needs `ffmpeg` and `ffprobe` on
-`PATH`, or explicit paths via `--ffmpeg` and `--ffprobe`. If you want to run
-the full COLMAP pipeline, also provide a COLMAP executable via
-`--colmap-executable`.
+`PATH`, or explicit paths via `--ffmpeg` and `--ffprobe`. To run the COLMAP
+reconstruction that
+[InstantSplat](https://github.com/yindaheng98/InstantSplat) continues from,
+also provide a COLMAP executable via `--colmap-executable`.
 
-Extract a Neural 3D Video scene and write per-frame COLMAP text models:
+Extract a Neural 3D Video scene and write per-frame COLMAP text models for
+[InstantSplat](https://github.com/yindaheng98/InstantSplat):
 
 ```bash
 python -m nvs2colmap.n3dv \
@@ -90,7 +94,8 @@ python -m nvs2colmap.n3dv \
   --n-frames 300
 ```
 
-Run the full COLMAP pipeline for each frame:
+Run COLMAP reconstruction for each frame, leaving undistortion to
+[InstantSplat](https://github.com/yindaheng98/InstantSplat):
 
 ```bash
 python -m nvs2colmap.n3dv \
@@ -105,7 +110,8 @@ python -m nvs2colmap.n3dv \
 ```
 
 Link a Dynamic 3D Gaussians scene, including its masks, and write per-frame
-COLMAP text models:
+COLMAP text models for
+[InstantSplat](https://github.com/yindaheng98/InstantSplat):
 
 ```bash
 python -m nvs2colmap.dynamic3dgs \
@@ -116,16 +122,20 @@ python -m nvs2colmap.dynamic3dgs \
 For Neural 3D Video scenes, decoded frames are written to `frame*/images` by
 default, and the command also writes `frame*/sparse/0` text models. With
 `--use-colmap`, decoded frames are written to `frame*/input`, and each frame
-additionally gets the standard COLMAP outputs such as `distorted/`, `images/`,
-`sparse/`, and `stereo/`. When `--start-number N` is provided, decoding starts
-from source video frame `N`, and the generated folders/images are also numbered
-from `N`.
+additionally gets the COLMAP workspace under `distorted/`, including
+`distorted/sparse/0`.
+[InstantSplat](https://github.com/yindaheng98/InstantSplat) undistorts that
+workspace. When `--start-number N` is provided, decoding starts from source
+video frame `N`, and the generated folders/images are also numbered from `N`.
 
 For Dynamic 3D Gaussians scenes, images from both `train_meta.json` and
 `test_meta.json` are hardlinked into `frame*/images`, and included masks are
 hardlinked into `frame*/image_masks` (`cam01.jpg` pairs with `cam01.jpg.png`).
 `--no-train-camera` and `--no-test-camera` drop one split. The same
 `--use-colmap` switch writes images to `frame*/input`, masks to
-`frame*/input_mask`, and runs COLMAP.
+`frame*/input_mask`, and runs COLMAP through mapping.
+[InstantSplat](https://github.com/yindaheng98/InstantSplat) undistorts both.
+That switch does not write `init_pt_cld.npz` into `sparse/0/points3D.ply`;
+the reconstructed points stay in `distorted/sparse/0`.
 `--start-number` uses the same 1-based output numbering; source file
 `000000.jpg` is frame `1`.

{nvs2colmap-0.3.2 → nvs2colmap-0.4.0}/README.md

@@ -2,6 +2,8 @@
 
 Utilities for converting novel view synthesis datasets to COLMAP format.
 
+**These scenes are prepared for [InstantSplat](https://github.com/yindaheng98/InstantSplat). The default commands write known-pose `sparse/0` text models and do not call COLMAP. `--use-colmap` runs feature extraction, matching, triangulation, and mapping, then stops at `distorted/sparse/0`. InstantSplat undistorts images and masks together with `image_undistorter` and `mask_undistorter`. This repository does not undistort, because `image_undistorter` alone leaves masks untouched.**
+
 ## Supported Formats
 
 - **Neural 3D Video Dataset**: scenes with `poses_bounds.npy` and one `mp4`
@@ -36,11 +38,13 @@ pip install numpy plyfile torch
 ```
 
 For Neural 3D Video scenes, the command also needs `ffmpeg` and `ffprobe` on
-`PATH`, or explicit paths via `--ffmpeg` and `--ffprobe`. If you want to run
-the full COLMAP pipeline, also provide a COLMAP executable via
-`--colmap-executable`.
+`PATH`, or explicit paths via `--ffmpeg` and `--ffprobe`. To run the COLMAP
+reconstruction that
+[InstantSplat](https://github.com/yindaheng98/InstantSplat) continues from,
+also provide a COLMAP executable via `--colmap-executable`.
 
-Extract a Neural 3D Video scene and write per-frame COLMAP text models:
+Extract a Neural 3D Video scene and write per-frame COLMAP text models for
+[InstantSplat](https://github.com/yindaheng98/InstantSplat):
 
 ```bash
 python -m nvs2colmap.n3dv \
@@ -61,7 +65,8 @@ python -m nvs2colmap.n3dv \
   --n-frames 300
 ```
 
-Run the full COLMAP pipeline for each frame:
+Run COLMAP reconstruction for each frame, leaving undistortion to
+[InstantSplat](https://github.com/yindaheng98/InstantSplat):
 
 ```bash
 python -m nvs2colmap.n3dv \
@@ -76,7 +81,8 @@ python -m nvs2colmap.n3dv \
 ```
 
 Link a Dynamic 3D Gaussians scene, including its masks, and write per-frame
-COLMAP text models:
+COLMAP text models for
+[InstantSplat](https://github.com/yindaheng98/InstantSplat):
 
 ```bash
 python -m nvs2colmap.dynamic3dgs \
@@ -87,16 +93,20 @@ python -m nvs2colmap.dynamic3dgs \
 For Neural 3D Video scenes, decoded frames are written to `frame*/images` by
 default, and the command also writes `frame*/sparse/0` text models. With
 `--use-colmap`, decoded frames are written to `frame*/input`, and each frame
-additionally gets the standard COLMAP outputs such as `distorted/`, `images/`,
-`sparse/`, and `stereo/`. When `--start-number N` is provided, decoding starts
-from source video frame `N`, and the generated folders/images are also numbered
-from `N`.
+additionally gets the COLMAP workspace under `distorted/`, including
+`distorted/sparse/0`.
+[InstantSplat](https://github.com/yindaheng98/InstantSplat) undistorts that
+workspace. When `--start-number N` is provided, decoding starts from source
+video frame `N`, and the generated folders/images are also numbered from `N`.
 
 For Dynamic 3D Gaussians scenes, images from both `train_meta.json` and
 `test_meta.json` are hardlinked into `frame*/images`, and included masks are
 hardlinked into `frame*/image_masks` (`cam01.jpg` pairs with `cam01.jpg.png`).
 `--no-train-camera` and `--no-test-camera` drop one split. The same
 `--use-colmap` switch writes images to `frame*/input`, masks to
-`frame*/input_mask`, and runs COLMAP.
+`frame*/input_mask`, and runs COLMAP through mapping.
+[InstantSplat](https://github.com/yindaheng98/InstantSplat) undistorts both.
+That switch does not write `init_pt_cld.npz` into `sparse/0/points3D.ply`;
+the reconstructed points stay in `distorted/sparse/0`.
 `--start-number` uses the same 1-based output numbering; source file
 `000000.jpg` is frame `1`.

{nvs2colmap-0.3.2 → nvs2colmap-0.4.0}/nvs2colmap/colmap.py

@@ -10,7 +10,6 @@ from nvs2colmap.write_model import CameraModel
 from nvs2colmap.utils.colmap import (
     exhaustive_matcher,
     feature_extractor,
-    image_undistorter,
     mapper,
     point_triangulator,
     read_db,
@@ -65,10 +64,6 @@ def run_colmap(
     if mapper(str(folder), str(mapper_input_path), colmap_executable=colmap_executable) != 0:
         raise RuntimeError("Mapping failed")
 
-    # To fit sparse init in instantsplat
-    if image_undistorter(str(folder), colmap_executable=colmap_executable) != 0:
-        raise RuntimeError("Image undistortion failed")
-
 
 def run_video_colmap(
     output_pattern: Path,

{nvs2colmap-0.3.2 → nvs2colmap-0.4.0}/nvs2colmap/dynamic3dgs/__main__.py

@@ -56,8 +56,8 @@ def parse_args() -> argparse.Namespace:
         "--use-colmap",
         action="store_true",
         help=(
-            "Run COLMAP feature extraction, matching, triangulation, mapping, "
-            "and undistortion instead of only writing sparse/0 text models."
+            "Run COLMAP feature extraction, matching, triangulation, and mapping "
+            "instead of only writing sparse/0 text models."
         ),
     )
     parser.add_argument(
@@ -115,6 +115,12 @@ def main() -> None:
             start_number=args.start_number,
             image_extension="",
         )
+        write_init_point_cloud(
+            npz_path=folder / "init_pt_cld.npz",
+            output_pattern=frame_output_pattern / "sparse" / "0" / "points3D.ply",
+            n_frames=n_frames,
+            start_number=args.start_number,
+        )
     else:
         run_video_colmap(
             output_pattern=frame_output_pattern,
@@ -126,13 +132,6 @@ def main() -> None:
             use_gpu=args.colmap_use_gpu,
         )
 
-    write_init_point_cloud(
-        npz_path=folder / "init_pt_cld.npz",
-        output_pattern=frame_output_pattern / "sparse" / "0" / "points3D.ply",
-        n_frames=n_frames,
-        start_number=args.start_number,
-    )
-
     print(f"Done: {folder}")
 
 

{nvs2colmap-0.3.2 → nvs2colmap-0.4.0}/nvs2colmap/n3dv/__main__.py

@@ -73,8 +73,8 @@ def parse_args() -> argparse.Namespace:
         "--use-colmap",
         action="store_true",
         help=(
-            "Run COLMAP feature extraction, matching, triangulation, mapping, "
-            "and undistortion instead of only writing sparse/0 text models."
+            "Run COLMAP feature extraction, matching, triangulation, and mapping "
+            "instead of only writing sparse/0 text models."
         ),
     )
     parser.add_argument(

{nvs2colmap-0.3.2 → nvs2colmap-0.4.0}/nvs2colmap/utils/__init__.py

@@ -4,7 +4,6 @@ from .colmap import (
     execute,
     exhaustive_matcher,
     feature_extractor,
-    image_undistorter,
     mapper,
     model_converter_bin,
     model_converter_txt,
@@ -21,7 +20,6 @@ __all__ = [
     "extract_video_frames",
     "extract_video_frames_parallel",
     "feature_extractor",
-    "image_undistorter",
     "mapper",
     "matrix_to_quaternion",
     "model_converter_bin",

{nvs2colmap-0.3.2 → nvs2colmap-0.4.0}/nvs2colmap/utils/colmap.py

@@ -62,7 +62,6 @@ def mapper(folder, mapper_input_path, colmap_executable="colmap"):
         colmap_executable, "mapper",
         "--database_path", os.path.join(folder, "distorted", "database.db"),
         "--image_path", os.path.join(folder, "input"),
-        "--Mapper.ba_global_function_tolerance=0.000001",
         "--input_path", mapper_input_path,
         "--output_path", os.path.join(folder, "distorted", "sparse", "0")
     ]
@@ -91,14 +90,3 @@ def model_converter_bin(folder, colmap_executable="colmap"):
         "--output_type=BIN",
     ]
     return execute(cmd)
-
-
-def image_undistorter(folder, colmap_executable="colmap"):
-    cmd = [
-        colmap_executable, "image_undistorter",
-        "--image_path", os.path.join(folder, "input"),
-        "--input_path", os.path.join(folder, "distorted", "sparse", "0"),
-        "--output_path", folder,
-        "--output_type=COLMAP",
-    ]
-    return execute(cmd)

{nvs2colmap-0.3.2 → nvs2colmap-0.4.0}/nvs2colmap.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nvs2colmap
-Version: 0.3.2
+Version: 0.4.0
 Summary: Utilities for converting novel view synthesis datasets to COLMAP format.
 Author-email: Howard Yin <yindaheng98@gmail.com>
 Maintainer-email: Howard Yin <yindaheng98@gmail.com>
@@ -31,6 +31,8 @@ Dynamic: license-file
 
 Utilities for converting novel view synthesis datasets to COLMAP format.
 
+**These scenes are prepared for [InstantSplat](https://github.com/yindaheng98/InstantSplat). The default commands write known-pose `sparse/0` text models and do not call COLMAP. `--use-colmap` runs feature extraction, matching, triangulation, and mapping, then stops at `distorted/sparse/0`. InstantSplat undistorts images and masks together with `image_undistorter` and `mask_undistorter`. This repository does not undistort, because `image_undistorter` alone leaves masks untouched.**
+
 ## Supported Formats
 
 - **Neural 3D Video Dataset**: scenes with `poses_bounds.npy` and one `mp4`
@@ -65,11 +67,13 @@ pip install numpy plyfile torch
 ```
 
 For Neural 3D Video scenes, the command also needs `ffmpeg` and `ffprobe` on
-`PATH`, or explicit paths via `--ffmpeg` and `--ffprobe`. If you want to run
-the full COLMAP pipeline, also provide a COLMAP executable via
-`--colmap-executable`.
+`PATH`, or explicit paths via `--ffmpeg` and `--ffprobe`. To run the COLMAP
+reconstruction that
+[InstantSplat](https://github.com/yindaheng98/InstantSplat) continues from,
+also provide a COLMAP executable via `--colmap-executable`.
 
-Extract a Neural 3D Video scene and write per-frame COLMAP text models:
+Extract a Neural 3D Video scene and write per-frame COLMAP text models for
+[InstantSplat](https://github.com/yindaheng98/InstantSplat):
 
 ```bash
 python -m nvs2colmap.n3dv \
@@ -90,7 +94,8 @@ python -m nvs2colmap.n3dv \
   --n-frames 300
 ```
 
-Run the full COLMAP pipeline for each frame:
+Run COLMAP reconstruction for each frame, leaving undistortion to
+[InstantSplat](https://github.com/yindaheng98/InstantSplat):
 
 ```bash
 python -m nvs2colmap.n3dv \
@@ -105,7 +110,8 @@ python -m nvs2colmap.n3dv \
 ```
 
 Link a Dynamic 3D Gaussians scene, including its masks, and write per-frame
-COLMAP text models:
+COLMAP text models for
+[InstantSplat](https://github.com/yindaheng98/InstantSplat):
 
 ```bash
 python -m nvs2colmap.dynamic3dgs \
@@ -116,16 +122,20 @@ python -m nvs2colmap.dynamic3dgs \
 For Neural 3D Video scenes, decoded frames are written to `frame*/images` by
 default, and the command also writes `frame*/sparse/0` text models. With
 `--use-colmap`, decoded frames are written to `frame*/input`, and each frame
-additionally gets the standard COLMAP outputs such as `distorted/`, `images/`,
-`sparse/`, and `stereo/`. When `--start-number N` is provided, decoding starts
-from source video frame `N`, and the generated folders/images are also numbered
-from `N`.
+additionally gets the COLMAP workspace under `distorted/`, including
+`distorted/sparse/0`.
+[InstantSplat](https://github.com/yindaheng98/InstantSplat) undistorts that
+workspace. When `--start-number N` is provided, decoding starts from source
+video frame `N`, and the generated folders/images are also numbered from `N`.
 
 For Dynamic 3D Gaussians scenes, images from both `train_meta.json` and
 `test_meta.json` are hardlinked into `frame*/images`, and included masks are
 hardlinked into `frame*/image_masks` (`cam01.jpg` pairs with `cam01.jpg.png`).
 `--no-train-camera` and `--no-test-camera` drop one split. The same
 `--use-colmap` switch writes images to `frame*/input`, masks to
-`frame*/input_mask`, and runs COLMAP.
+`frame*/input_mask`, and runs COLMAP through mapping.
+[InstantSplat](https://github.com/yindaheng98/InstantSplat) undistorts both.
+That switch does not write `init_pt_cld.npz` into `sparse/0/points3D.ply`;
+the reconstructed points stay in `distorted/sparse/0`.
 `--start-number` uses the same 1-based output numbering; source file
 `000000.jpg` is frame `1`.

{nvs2colmap-0.3.2 → nvs2colmap-0.4.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "nvs2colmap"
-version = "0.3.2"
+version = "0.4.0"
 description = "Utilities for converting novel view synthesis datasets to COLMAP format."
 readme = "README.md"
 authors = [{ name = "Howard Yin", email = "yindaheng98@gmail.com" }]