reduced-3dgs 1.10.4__cp311-cp311-win_amd64.whl → 1.10.12__cp311-cp311-win_amd64.whl

reduced_3dgs/combinations.py

@@ -97,11 +97,17 @@ def BaseFullPrunerInDensifyTrainer(
 
 
 def DepthFullPruningTrainer(model: GaussianModel, scene_extent: float, dataset: TrainableCameraDataset, *args, **kwargs):
-    return DepthTrainerWrapper(BaseFullPruningTrainer, model, scene_extent, *args, dataset=dataset, **kwargs)
+    return DepthTrainerWrapper(
+        BaseFullPruningTrainer,
+        model, scene_extent, dataset,
+        *args, **kwargs)
 
 
 def DepthFullPrunerInDensifyTrainer(model: GaussianModel, scene_extent: float, dataset: TrainableCameraDataset, *args, **kwargs):
-    return DepthTrainerWrapper(BaseFullPrunerInDensifyTrainer, model, scene_extent, *args, dataset=dataset, **kwargs)
+    return DepthTrainerWrapper(
+        BaseFullPrunerInDensifyTrainer,
+        model, scene_extent, dataset,
+        *args, **kwargs)
 
 
 def OpacityResetPruningTrainer(

reduced_3dgs/importance/combinations.py

@@ -52,11 +52,17 @@ def BaseImportancePrunerInDensifyTrainer(
 
 
 def DepthImportancePruningTrainer(model: GaussianModel, scene_extent: float, dataset: TrainableCameraDataset, *args, **kwargs):
-    return DepthTrainerWrapper(BaseImportancePruningTrainer, model, scene_extent, *args, dataset=dataset, **kwargs)
+    return DepthTrainerWrapper(
+        BaseImportancePruningTrainer,
+        model, scene_extent, dataset,
+        *args, **kwargs)
 
 
 def DepthImportancePrunerInDensifyTrainer(model: GaussianModel, scene_extent: float, dataset: TrainableCameraDataset, *args, **kwargs):
-    return DepthTrainerWrapper(BaseImportancePrunerInDensifyTrainer, model, scene_extent, *args, dataset=dataset, **kwargs)
+    return DepthTrainerWrapper(
+        BaseImportancePrunerInDensifyTrainer,
+        model, scene_extent, dataset,
+        *args, **kwargs)
 
 
 ImportancePruningTrainer = DepthImportancePruningTrainer

reduced_3dgs/pruning/combinations.py

@@ -54,11 +54,17 @@ def BasePrunerInDensifyTrainer(
 
 
 def DepthPruningTrainer(model: GaussianModel, scene_extent: float, dataset: TrainableCameraDataset, *args, **kwargs):
-    return DepthTrainerWrapper(BasePruningTrainer, model, scene_extent, *args, dataset=dataset, **kwargs)
+    return DepthTrainerWrapper(
+        BasePruningTrainer,
+        model, scene_extent, dataset,
+        *args, **kwargs)
 
 
 def DepthPrunerInDensifyTrainer(model: GaussianModel, scene_extent: float, dataset: TrainableCameraDataset, *args, **kwargs):
-    return DepthTrainerWrapper(BasePrunerInDensifyTrainer, model, scene_extent, *args, dataset=dataset, **kwargs)
+    return DepthTrainerWrapper(
+        BasePrunerInDensifyTrainer,
+        model, scene_extent, dataset,
+        *args, **kwargs)
 
 
 PruningTrainer = DepthPruningTrainer

reduced_3dgs/quantization/quantizer.py

@@ -4,7 +4,15 @@ from typing import Dict, Tuple
 import torch
 import torch.nn as nn
 import numpy as np
-from sklearn.cluster import MiniBatchKMeans as KMeans
+try:
+    from cuml.cluster import KMeans
+    kmeans_init = 'k-means||'
+except ImportError:
+    print("Cuml not found, using sklearn's MiniBatchKMeans for quantization.")
+    from sklearn.cluster import MiniBatchKMeans
+    from functools import partial
+    KMeans = partial(MiniBatchKMeans, batch_size=256 * os.cpu_count())
+    kmeans_init = 'k-means++'
 from gaussian_splatting import GaussianModel
 from plyfile import PlyData, PlyElement
 import numpy as np
@@ -65,9 +73,8 @@ class VectorQuantizer(AbstractQuantizer):
     def generate_codebook(self, values: torch.Tensor, num_clusters, init_codebook=None):
         kmeans = KMeans(
             n_clusters=num_clusters, tol=self.tol, max_iter=self.max_iter,
-            init='k-means++' if init_codebook is None else init_codebook.cpu().numpy(),
-            random_state=0, n_init="auto", verbose=0,
-            batch_size=256 * os.cpu_count()
+            init=kmeans_init if init_codebook is None else init_codebook.cpu().numpy(),
+            random_state=0, n_init="auto", verbose=1,
         )
         ids = torch.tensor(kmeans.fit_predict(values.cpu().numpy()), device=values.device)
         centers = torch.tensor(kmeans.cluster_centers_, dtype=values.dtype, device=values.device)

reduced_3dgs/train.py

@@ -14,8 +14,12 @@ from reduced_3dgs.quantization import AbstractQuantizer
 from reduced_3dgs.prepare import modes, prepare_gaussians, prepare_trainer
 
 
-def prepare_training(sh_degree: int, source: str, device: str, mode: str, trainable_camera: bool = False, load_ply: str = None, load_camera: str = None, load_depth=False, with_scale_reg=False, quantize: bool = False, load_quantized: str = None, configs={}):
-    dataset = prepare_dataset(source=source, device=device, trainable_camera=trainable_camera, load_camera=load_camera, load_depth=load_depth)
+def prepare_training(
+        sh_degree: int, source: str, device: str, mode: str,
+        trainable_camera: bool = False, load_ply: str = None, load_camera: str = None,
+        load_mask=True, load_depth=True,
+        with_scale_reg=False, quantize: bool = False, load_quantized: str = None, configs={}):
+    dataset = prepare_dataset(source=source, device=device, trainable_camera=trainable_camera, load_camera=load_camera, load_mask=load_mask, load_depth=load_depth)
     gaussians = prepare_gaussians(sh_degree=sh_degree, source=source, device=device, trainable_camera=trainable_camera, load_ply=load_ply)
     trainer, quantizer = prepare_trainer(gaussians=gaussians, dataset=dataset, mode=mode, with_scale_reg=with_scale_reg, quantize=quantize, load_quantized=load_quantized, configs=configs)
     return dataset, gaussians, trainer, quantizer
@@ -23,26 +27,39 @@ def prepare_training(sh_degree: int, source: str, device: str, mode: str, traina
 
 def training(dataset: CameraDataset, gaussians: GaussianModel, trainer: AbstractTrainer, quantizer: AbstractQuantizer, destination: str, iteration: int, save_iterations: List[int], device: str, empty_cache_every_step=False):
     shutil.rmtree(os.path.join(destination, "point_cloud"), ignore_errors=True)  # remove the previous point cloud
-    pbar = tqdm(range(1, iteration+1))
+    pbar = tqdm(range(1, iteration+1), dynamic_ncols=True, desc="Training")
     epoch = list(range(len(dataset)))
     epoch_psnr = torch.empty(3, 0, device=device)
+    epoch_maskpsnr = torch.empty(3, 0, device=device)
     ema_loss_for_log = 0.0
     avg_psnr_for_log = 0.0
+    avg_maskpsnr_for_log = 0.0
     for step in pbar:
         epoch_idx = step % len(dataset)
         if epoch_idx == 0:
             avg_psnr_for_log = epoch_psnr.mean().item()
+            avg_maskpsnr_for_log = epoch_maskpsnr.mean().item()
             epoch_psnr = torch.empty(3, 0, device=device)
+            epoch_maskpsnr = torch.empty(3, 0, device=device)
             random.shuffle(epoch)
         idx = epoch[epoch_idx]
         loss, out = trainer.step(dataset[idx])
         if empty_cache_every_step:
             torch.cuda.empty_cache()
         with torch.no_grad():
+            ground_truth_image = dataset[idx].ground_truth_image
+            rendered_image = out["render"]
+            epoch_psnr = torch.concat([epoch_psnr, psnr(rendered_image, ground_truth_image)], dim=1)
+            if dataset[idx].ground_truth_image_mask is not None:
+                ground_truth_maskimage = ground_truth_image * dataset[idx].ground_truth_image_mask
+                rendered_maskimage = rendered_image * dataset[idx].ground_truth_image_mask
+                epoch_maskpsnr = torch.concat([epoch_maskpsnr, psnr(rendered_maskimage, ground_truth_maskimage)], dim=1)
             ema_loss_for_log = 0.4 * loss.item() + 0.6 * ema_loss_for_log
-            epoch_psnr = torch.concat([epoch_psnr, psnr(out["render"], dataset[idx].ground_truth_image)], dim=1)
             if step % 10 == 0:
-                pbar.set_postfix({'epoch': step // len(dataset), 'loss': ema_loss_for_log, 'psnr': avg_psnr_for_log, 'n': gaussians._xyz.shape[0]})
+                postfix = {'epoch': step // len(dataset), 'loss': ema_loss_for_log, 'psnr': avg_psnr_for_log, 'n': gaussians._xyz.shape[0]}
+                if avg_maskpsnr_for_log > 0:
+                    postfix['psnr (mask)'] = avg_maskpsnr_for_log
+                pbar.set_postfix(postfix)
         if step in save_iterations:
             save_path = os.path.join(destination, "point_cloud", "iteration_" + str(step))
             os.makedirs(save_path, exist_ok=True)
@@ -68,6 +85,7 @@ if __name__ == "__main__":
     parser.add_argument("-l", "--load_ply", default=None, type=str)
     parser.add_argument("--load_camera", default=None, type=str)
     parser.add_argument("--quantize", action='store_true')
+    parser.add_argument("--no_image_mask", action="store_true")
     parser.add_argument("--no_depth_data", action='store_true')
     parser.add_argument("--with_scale_reg", action="store_true")
     parser.add_argument("--load_quantized", default=None, type=str)
@@ -83,7 +101,9 @@ if __name__ == "__main__":
     configs = {o.split("=", 1)[0]: eval(o.split("=", 1)[1]) for o in args.option}
     dataset, gaussians, trainer, quantizer = prepare_training(
         sh_degree=args.sh_degree, source=args.source, device=args.device, mode=args.mode, trainable_camera="camera" in args.mode,
-        load_ply=args.load_ply, load_camera=args.load_camera, load_depth=not args.no_depth_data, with_scale_reg=args.with_scale_reg,
+        load_ply=args.load_ply, load_camera=args.load_camera,
+        load_mask=not args.no_image_mask, load_depth=not args.no_depth_data,
+        with_scale_reg=args.with_scale_reg,
         quantize=args.quantize, load_quantized=args.load_quantized, configs=configs)
     dataset.save_cameras(os.path.join(args.destination, "cameras.json"))
     torch.cuda.empty_cache()

{reduced_3dgs-1.10.4.dist-info → reduced_3dgs-1.10.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: reduced_3dgs
-Version: 1.10.4
+Version: 1.10.12
 Summary: Refactored code for the paper "Reducing the Memory Footprint of 3D Gaussian Splatting"
 Home-page: https://github.com/yindaheng98/reduced-3dgs
 Author: yindaheng98
@@ -8,13 +8,8 @@ Author-email: yindaheng98@gmail.com
 Classifier: Programming Language :: Python :: 3
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: tqdm
-Requires-Dist: plyfile
-Requires-Dist: scikit-learn
-Requires-Dist: torch
-Requires-Dist: torchvision
-Requires-Dist: numpy
 Requires-Dist: gaussian-splatting
+Requires-Dist: scikit-learn
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -40,47 +35,35 @@ This repository contains the **refactored Python code for [Reduced-3DGS](https:/
 
 * [Pytorch](https://pytorch.org/) (v2.4 or higher recommended)
 * [CUDA Toolkit](https://developer.nvidia.com/cuda-12-4-0-download-archive) (12.4 recommended, should match with PyTorch version)
+* (Optional) [cuML](https://github.com/rapidsai/cuml) for faster vector quantization
 
-## Install (PyPI)
-
+(Optional) If you have trouble with [`gaussian-splatting`](https://github.com/yindaheng98/gaussian-splatting), try to install it from source:
 ```sh
-pip install --upgrade reduced-3dgs
+pip install wheel setuptools
+pip install --upgrade git+https://github.com/yindaheng98/gaussian-splatting.git@master --no-build-isolation
 ```
 
-## Install (Build from source)
-
-```sh
-pip install --upgrade git+https://github.com/yindaheng98/reduced-3dgs.git@main
-```
-If you have trouble with [`gaussian-splatting`](https://github.com/yindaheng98/gaussian-splatting), you can install it from source:
-```sh
-pip install --upgrade git+https://github.com/yindaheng98/gaussian-splatting.git@master
-```
+## PyPI Install
 
-## Install (Development)
-
-Install [`gaussian-splatting`](https://github.com/yindaheng98/gaussian-splatting).
-You can download the wheel from [PyPI](https://pypi.org/project/gaussian-splatting/):
 ```shell
-pip install --upgrade gaussian-splatting
+pip install --upgrade reduced-3dgs
 ```
-Alternatively, install the latest version from the source:
-```sh
-pip install --upgrade git+https://github.com/yindaheng98/gaussian-splatting.git@master
+or
+build latest from source:
+```shell
+pip install wheel setuptools
+pip install --upgrade git+https://github.com/yindaheng98/reduced-3dgs.git@main --no-build-isolation
 ```
 
+### Development Install
+
 ```shell
 git clone --recursive https://github.com/yindaheng98/reduced-3dgs
 cd reduced-3dgs
-pip install tqdm plyfile scikit-learn numpy tifffile triton xformers
+pip install scikit-learn
 pip install --target . --upgrade --no-deps .
 ```
 
-(Optional) If you prefer not to install `gaussian-splatting` in your environment, you can install it in your `reduced-3dgs` directory:
-```sh
-pip install --target . --no-deps --upgrade git+https://github.com/yindaheng98/gaussian-splatting.git@master
-```
-
 ## Quick Start
 
 1. Download the dataset (T&T+DB COLMAP dataset, size 650MB):

{reduced_3dgs-1.10.4.dist-info → reduced_3dgs-1.10.12.dist-info}/RECORD

@@ -1,29 +1,29 @@
 reduced_3dgs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-reduced_3dgs/combinations.py,sha256=k4ErxpAscCqJMtVXZ29KGQjw2VoZMV0W3V4u3nj0e-Y,9401
+reduced_3dgs/combinations.py,sha256=dRrtTIQLggUP22Olp0DVSlD0C8YDgnrpTlrCcGZyWM0,9441
 reduced_3dgs/prepare.py,sha256=MFUUckRHKfgcva4ZOBxfPFyE95N-OlCQLplpmEPuzOk,4440
 reduced_3dgs/quantize.py,sha256=BVqBb2tQgiP3hap5-OByD8VELtJJGfEeFzaVFyzCJZU,2572
-reduced_3dgs/train.py,sha256=yRQPQv-hTOBQN-tqGHYs2aIZ0AbWq158CXpthYN2cfw,5666
-reduced_3dgs/diff_gaussian_rasterization/_C.cp311-win_amd64.pyd,sha256=z_fsa8uGn_5Q4gGNBlhZY0dMwbc8u-uNwe_8qecm6J8,1632256
+reduced_3dgs/train.py,sha256=P9GCoEVl_VGldKuA3ycj1nea5rTc3xqu_f02a8oe-Lc,6734
+reduced_3dgs/diff_gaussian_rasterization/_C.cp311-win_amd64.pyd,sha256=aWFuGgyzyWa0cjbPxVD-hytfzFy7OoBp2cmWhUjlxCQ,1623552
 reduced_3dgs/diff_gaussian_rasterization/__init__.py,sha256=oV6JjTc-50MscX4XHeIWSgLr3l8Y25knBIs-0gRbJr4,7932
 reduced_3dgs/importance/__init__.py,sha256=neJsbY5cLikEGBQGdR4MjwCQ5VWVikT1357DwL0EtWU,289
-reduced_3dgs/importance/combinations.py,sha256=eAdykeTdvRGCHxskjILQnZVaqQVvwC-0wMxdgYMeeDs,2922
+reduced_3dgs/importance/combinations.py,sha256=F9IYDZ6iquZw5Djn2An88dlp2MUGieAyuZyVaDZdSts,2962
 reduced_3dgs/importance/trainer.py,sha256=Sj4ORvoYtFT7z3hifzFZDfhFyqumHraXyk3vMVtk0AU,12661
-reduced_3dgs/importance/diff_gaussian_rasterization/_C.cp311-win_amd64.pyd,sha256=sKkkpqtRlM-FWeyXzpqdQ_XtmEF_7OYEoAvR8ab_uws,1315840
+reduced_3dgs/importance/diff_gaussian_rasterization/_C.cp311-win_amd64.pyd,sha256=F8XFzTme9bbxV3mo_q9aW_O-UzCdLnb0Hb_kjyLE0oA,1309696
 reduced_3dgs/importance/diff_gaussian_rasterization/__init__.py,sha256=Tix8auyXBb_QFQtXrV3sLE9kdnl5zgHH0BbqcFzDp84,12850
 reduced_3dgs/pruning/__init__.py,sha256=E_YxJ9cDV_B6EJbYUBEcuRYMIht_C72rI1VJUXFCLpM,201
-reduced_3dgs/pruning/combinations.py,sha256=QhXt2C7pTXhwzp9hPL9dVdiQzz0cUQpm5qljqytPEsM,2345
+reduced_3dgs/pruning/combinations.py,sha256=xO39d08DEsDnKI5np_1xQ4H29O486Q_cThLfWhlH810,2385
 reduced_3dgs/pruning/trainer.py,sha256=JJml-uYfDfUpbsjRNZbIvnUYYslVgFXkhejbkYSo0s4,6542
 reduced_3dgs/quantization/__init__.py,sha256=1z1xMn3yj9u7cR9JizGrI3WSyIES_Tqq6oDquvglSeo,225
 reduced_3dgs/quantization/abc.py,sha256=rsi8HFRwQCltWTYiJ3BpygtQDT7hK6J01jKMOboOY8w,1910
 reduced_3dgs/quantization/exclude_zeros.py,sha256=fKSgjHous4OpdI6mQi9z23if9jnbB79w2jChpxkCJWw,2381
-reduced_3dgs/quantization/quantizer.py,sha256=lsaJ4yjxquC9XCDZPTGIKe8EgHAEwmVw9rt73oezjmc,17686
+reduced_3dgs/quantization/quantizer.py,sha256=2myyBsYPGbzjZhjpKnYMYcvk6INqeds7wRdBRbIPki4,17948
 reduced_3dgs/quantization/wrapper.py,sha256=cyXqfJgo9b3fS7DYXxOk5LmQudvrEhweOebFsjRnXiQ,2549
 reduced_3dgs/shculling/__init__.py,sha256=nP2BejDCUdCmJNRbg0hfhHREO6jyZXwIcRiw6ttVgqo,149
 reduced_3dgs/shculling/gaussian_model.py,sha256=f8QWaL09vaV9Tcf6Dngjg_Fmk1wTQPAjWhuhI_N02Y8,2877
 reduced_3dgs/shculling/trainer.py,sha256=9hwR77djhZpyf-URhwKHjnLbe0ZAOS-DIw58RzkcHXQ,6369
-reduced_3dgs/simple_knn/_C.cp311-win_amd64.pyd,sha256=cDeScla9Mn6aDP_HNHhIIiFCwMUL78XtOid7PgOQ2bA,1263616
-reduced_3dgs-1.10.4.dist-info/licenses/LICENSE.md,sha256=LQ4_LAqlncGkg_mQy5ykMAFtQDSPB0eKmIEtBut0yjw,4916
-reduced_3dgs-1.10.4.dist-info/METADATA,sha256=TfBJNYmRSs23HhMOj15mrTFzryN015ZgGTeqUMKza7w,13015
-reduced_3dgs-1.10.4.dist-info/WHEEL,sha256=JLOMsP7F5qtkAkINx5UnzbFguf8CqZeraV8o04b0I8I,101
-reduced_3dgs-1.10.4.dist-info/top_level.txt,sha256=PpU5aT3-baSCdqCtTaZknoB32H93UeKCkYDkRCCZMEI,13
-reduced_3dgs-1.10.4.dist-info/RECORD,,
+reduced_3dgs/simple_knn/_C.cp311-win_amd64.pyd,sha256=wSW7NtSfC_zKK3EieP3moJtC-WZkiXbnDzbmz-A8opA,1256448
+reduced_3dgs-1.10.12.dist-info/licenses/LICENSE.md,sha256=LQ4_LAqlncGkg_mQy5ykMAFtQDSPB0eKmIEtBut0yjw,4916
+reduced_3dgs-1.10.12.dist-info/METADATA,sha256=7cQgH63LmWATezhRqXDPA6ytT_Ld9mYXKppGqvR8QTw,12404
+reduced_3dgs-1.10.12.dist-info/WHEEL,sha256=JLOMsP7F5qtkAkINx5UnzbFguf8CqZeraV8o04b0I8I,101
+reduced_3dgs-1.10.12.dist-info/top_level.txt,sha256=PpU5aT3-baSCdqCtTaZknoB32H93UeKCkYDkRCCZMEI,13
+reduced_3dgs-1.10.12.dist-info/RECORD,,