[DRAFT] Gaussian Opacity Fields implementation

examples/benchmark_mipnerf360.py

@@ -0,0 +1,93 @@
+# Training script for the Mip-NeRF 360 dataset
+
+import os
+import GPUtil
+from concurrent.futures import ThreadPoolExecutor
+import time
+import glob
+
+# 9 scenes
+# scenes = ["bicycle", "bonsai", "counter", "flowers", "garden", "stump", "treehill", "kitchen", "room"]
+# factors = [4, 2, 2, 4, 4, 4, 4, 2, 2]
+
+# 7 scenes
+scenes = ["bicycle", "bonsai", "counter", "garden", "stump", "kitchen", "room"]
+factors = [4, 2, 2, 4, 4, 2, 2]
+
+excluded_gpus = set([])
+
+result_dir = "results/benchmark_mipsplatting_cuda3D"
+
+dry_run = False
+
+jobs = list(zip(scenes, factors))
+
+
+def train_scene(gpu, scene, factor):
+    # train without eval
+    cmd = f"OMP_NUM_THREADS=4 CUDA_VISIBLE_DEVICES={gpu} python simple_trainer_mip_splatting.py --eval_steps -1 --disable_viewer --data_factor {factor} --data_dir data/360_v2/{scene} --result_dir {result_dir}/{scene} --antialiased --kernel_size 0.1"
+    print(cmd)
+    if not dry_run:
+        os.system(cmd)
+
+    # eval and render for all the ckpts
+    ckpts = glob.glob(f"{result_dir}/{scene}/ckpts/*.pt")
+    for ckpt in ckpts:
+        cmd = f"OMP_NUM_THREADS=4 CUDA_VISIBLE_DEVICES={gpu} python simple_trainer_mip_splatting.py --disable_viewer --data_factor {factor} --data_dir data/360_v2/{scene} --result_dir {result_dir}/{scene} --ckpt {ckpt} --antialiased --kernel_size 0.1"
+        print(cmd)
+        if not dry_run:
+            os.system(cmd)
+
+    return True
+
+
+def worker(gpu, scene, factor):
+    print(f"Starting job on GPU {gpu} with scene {scene}\n")
+    train_scene(gpu, scene, factor)
+    print(f"Finished job on GPU {gpu} with scene {scene}\n")
+    # This worker function starts a job and returns when it's done.
+
+
+def dispatch_jobs(jobs, executor):
+    future_to_job = {}
+    reserved_gpus = set()  # GPUs that are slated for work but may not be active yet
+
+    while jobs or future_to_job:
+        # Get the list of available GPUs, not including those that are reserved.
+        all_available_gpus = set(
+            GPUtil.getAvailable(order="first", limit=10, maxMemory=0.1, maxLoad=0.1)
+        )
+        # all_available_gpus = set([0,1,2,3])
+        available_gpus = list(all_available_gpus - reserved_gpus - excluded_gpus)
+
+        # Launch new jobs on available GPUs
+        while available_gpus and jobs:
+            gpu = available_gpus.pop(0)
+            job = jobs.pop(0)
+            future = executor.submit(
+                worker, gpu, *job
+            )  # Unpacking job as arguments to worker
+            future_to_job[future] = (gpu, job)
+
+            reserved_gpus.add(gpu)  # Reserve this GPU until the job starts processing
+
+        # Check for completed jobs and remove them from the list of running jobs.
+        # Also, release the GPUs they were using.
+        done_futures = [future for future in future_to_job if future.done()]
+        for future in done_futures:
+            job = future_to_job.pop(
+                future
+            )  # Remove the job associated with the completed future
+            gpu = job[0]  # The GPU is the first element in each job tuple
+            reserved_gpus.discard(gpu)  # Release this GPU
+            print(f"Job {job} has finished., rellasing GPU {gpu}")
+        # (Optional) You might want to introduce a small delay here to prevent this loop from spinning very fast
+        # when there are no GPUs available.
+        time.sleep(5)
+
+    print("All jobs have been processed.")
+
+
+# Using ThreadPoolExecutor to manage the thread pool
+with ThreadPoolExecutor(max_workers=8) as executor:
+    dispatch_jobs(jobs, executor)

examples/benchmark_mipnerf360_stmt.py

@@ -0,0 +1,115 @@
+# Training script for the Mip-NeRF 360 dataset
+# The model is trained with downsampling factor 8 and rendered with downsampling factor 1, 2, 4, 8
+
+import os
+import GPUtil
+from concurrent.futures import ThreadPoolExecutor
+import time
+import glob
+
+# 9 scenes
+# scenes = ["bicycle", "bonsai", "counter", "flowers", "garden", "stump", "treehill", "kitchen", "room"]
+# factors = [4, 2, 2, 4, 4, 4, 4, 2, 2]
+
+# 7 scenes
+scenes = ["bicycle", "bonsai", "counter", "garden", "stump", "kitchen", "room"]
+factors = [8] * len(scenes)
+
+excluded_gpus = set([])
+
+# classic
+result_dir = "results/benchmark_stmt"
+# antialiased
+result_dir = "results/benchmark_antialiased_stmt"
+# mip-splatting
+# result_dir = "results/benchmark_mipsplatting_stmt"
+
+dry_run = False
+
+jobs = list(zip(scenes, factors))
+
+
+def train_scene(gpu, scene, factor):
+    # train without eval
+    # classic
+    # cmd = f"OMP_NUM_THREADS=4 CUDA_VISIBLE_DEVICES={gpu} python simple_trainer.py --eval_steps -1 --disable_viewer --data_factor {factor} --data_dir data/360_v2/{scene} --result_dir {result_dir}/{scene}"
+
+    # anti-aliased
+    # cmd = f"OMP_NUM_THREADS=4 CUDA_VISIBLE_DEVICES={gpu} python simple_trainer.py --eval_steps -1 --disable_viewer --data_factor {factor} --data_dir data/360_v2/{scene} --result_dir {result_dir}/{scene} --antialiased"
+
+    # mip-splatting
+    cmd = f"OMP_NUM_THREADS=4 CUDA_VISIBLE_DEVICES={gpu} python simple_trainer_mip_splatting.py --eval_steps -1 --disable_viewer --data_factor {factor} --data_dir data/360_v2/{scene} --result_dir {result_dir}/{scene} --antialiased --kernel_size 0.1"
+    print(cmd)
+    if not dry_run:
+        os.system(cmd)
+
+    # eval and render for all the ckpts
+    ckpts = glob.glob(f"{result_dir}/{scene}/ckpts/*.pt")
+    for ckpt in ckpts:
+        for test_factor in [1, 2, 4, 8]:
+            # classic
+            # cmd = f"OMP_NUM_THREADS=4 CUDA_VISIBLE_DEVICES={gpu} python simple_trainer.py --disable_viewer --data_factor {test_factor} --data_dir data/360_v2/{scene} --result_dir {result_dir}/{scene}_{test_factor} --ckpt {ckpt}"
+
+            # anti-aliased
+            # cmd = f"OMP_NUM_THREADS=4 CUDA_VISIBLE_DEVICES={gpu} python simple_trainer.py --disable_viewer --data_factor {test_factor} --data_dir data/360_v2/{scene} --result_dir {result_dir}/{scene}_{test_factor} --ckpt {ckpt} --antialiased"
+
+            # mip-splatting
+            cmd = f"OMP_NUM_THREADS=4 CUDA_VISIBLE_DEVICES={gpu} python simple_trainer_mip_splatting.py --disable_viewer --data_factor {test_factor} --data_dir data/360_v2/{scene} --result_dir {result_dir}/{scene}_{test_factor} --ckpt {ckpt} --antialiased --kernel_size 0.1"
+            print(cmd)
+            if not dry_run:
+                os.system(cmd)
+
+    return True
+
+
+def worker(gpu, scene, factor):
+    print(f"Starting job on GPU {gpu} with scene {scene}\n")
+    train_scene(gpu, scene, factor)
+    print(f"Finished job on GPU {gpu} with scene {scene}\n")
+    # This worker function starts a job and returns when it's done.
+
+
+def dispatch_jobs(jobs, executor):
+    future_to_job = {}
+    reserved_gpus = set()  # GPUs that are slated for work but may not be active yet
+
+    while jobs or future_to_job:
+        # Get the list of available GPUs, not including those that are reserved.
+        all_available_gpus = set(
+            GPUtil.getAvailable(order="first", limit=10, maxMemory=0.1, maxLoad=0.1)
+        )
+        # all_available_gpus = set([0,1,2,3])
+        available_gpus = list(all_available_gpus - reserved_gpus - excluded_gpus)
+
+        # Launch new jobs on available GPUs
+        while available_gpus and jobs:
+            gpu = available_gpus.pop(0)
+            job = jobs.pop(0)
+            future = executor.submit(
+                worker, gpu, *job
+            )  # Unpacking job as arguments to worker
+            future_to_job[future] = (gpu, job)
+
+            reserved_gpus.add(gpu)  # Reserve this GPU until the job starts processing
+            time.sleep(2)
+
+        # Check for completed jobs and remove them from the list of running jobs.
+        # Also, release the GPUs they were using.
+        done_futures = [future for future in future_to_job if future.done()]
+        for future in done_futures:
+            job = future_to_job.pop(
+                future
+            )  # Remove the job associated with the completed future
+            gpu = job[0]  # The GPU is the first element in each job tuple
+            reserved_gpus.discard(gpu)  # Release this GPU
+            print(f"Job {job} has finished., rellasing GPU {gpu}")
+        # (Optional) You might want to introduce a small delay here to prevent this loop from spinning very fast
+        # when there are no GPUs available.
+        time.sleep(5)
+
+    print("All jobs have been processed.")
+
+
+# Using ThreadPoolExecutor to manage the thread pool
+with ThreadPoolExecutor(max_workers=8) as executor:
+    dispatch_jobs(jobs, executor)

examples/datasets/colmap.py

@@ -182,6 +182,7 @@ def __init__(
         self.image_names = image_names  # List[str], (num_images,)
         self.image_paths = image_paths  # List[str], (num_images,)
         self.camtoworlds = camtoworlds  # np.ndarray, (num_images, 4, 4)
+        self.worldtocams = np.linalg.inv(camtoworlds)  # np.ndarray, (num_images, 4, 4)
         self.camera_ids = camera_ids  # List[int], (num_images,)
         self.Ks_dict = Ks_dict  # Dict of camera_id -> K
         self.params_dict = params_dict  # Dict of camera_id -> params
@@ -254,6 +255,7 @@ def __getitem__(self, item: int) -> Dict[str, Any]:
         K = self.parser.Ks_dict[camera_id].copy()  # undistorted K
         params = self.parser.params_dict[camera_id]
         camtoworlds = self.parser.camtoworlds[index]
+        worldtocams = self.parser.worldtocams[index]
 
         if len(params) > 0:
             # Images are distorted. Undistort them.
@@ -277,6 +279,7 @@ def __getitem__(self, item: int) -> Dict[str, Any]:
         data = {
             "K": torch.from_numpy(K).float(),
             "camtoworld": torch.from_numpy(camtoworlds).float(),
+            "worldtocam": torch.from_numpy(worldtocams).float(),
             "image": torch.from_numpy(image).float(),
             "image_id": item,  # the index of the image in the dataset
         }

examples/datasets/download_dataset.py

@@ -9,9 +9,7 @@
 import tyro
 
 # dataset names
-dataset_names = Literal[
-    "mipnerf360",
-]
+dataset_names = Literal["mipnerf360",]
 
 # dataset urls
 urls = {"mipnerf360": "http://storage.googleapis.com/gresearch/refraw360/360_v2.zip"}

examples/show_mipnerf360.py

@@ -0,0 +1,51 @@
+import json
+import numpy as np
+import glob
+
+# 9 scenes
+# scenes = ['bicycle', 'flowers', 'garden', 'stump', 'treehill', 'room', 'counter', 'kitchen', 'bonsai']
+
+# outdoor scenes
+# scenes = scenes[:5]
+# indoor scenes
+# scenes = scenes[5:]
+
+# 7 scenes
+scenes = ["bicycle", "bonsai", "counter", "garden", "stump", "kitchen", "room"]
+
+result_dirs = ["results/benchmark"]
+result_dirs = ["results/benchmark_antialiased"]
+result_dirs = ["results/benchmark_mipsplatting"]
+result_dirs = ["results/benchmark_mipsplatting_cuda3D"]
+
+all_metrics = {"psnr": [], "ssim": [], "lpips": [], "num_GS": []}
+print(result_dirs)
+
+for scene in scenes:
+    print(scene, end=" ")
+    for result_dir in result_dirs:
+        json_files = glob.glob(f"{result_dir}/{scene}/stats/val_step29999.json")
+        for json_file in json_files:
+            # print(json_file)
+            data = json.load(open(json_file))
+            # print(data)
+
+            for k in ["psnr", "ssim", "lpips", "num_GS"]:
+                all_metrics[k].append(data[k])
+                print(f"{data[k]:.3f}", end=" ")
+            print()
+
+latex = []
+for k in ["psnr", "ssim", "lpips", "num_GS"]:
+    numbers = np.asarray(all_metrics[k]).mean(axis=0).tolist()
+    print(numbers)
+    numbers = [numbers]
+    if k == "PSNR":
+        numbers = [f"{x:.2f}" for x in numbers]
+    elif k == "num_GS":
+        num = numbers[0] / 1e6
+        numbers = [f"{num:.2f}"]
+    else:
+        numbers = [f"{x:.3f}" for x in numbers]
+    latex.extend(numbers)
+print(" | ".join(latex))

examples/show_mipnerf360_allscales.py

@@ -0,0 +1,45 @@
+import json
+import numpy as np
+import glob
+
+# 9 scenes
+# scenes = ['bicycle', 'flowers', 'garden', 'stump', 'treehill', 'room', 'counter', 'kitchen', 'bonsai']
+
+# outdoor scenes
+# scenes = scenes[:5]
+# indoor scenes
+# scenes = scenes[5:]
+
+# 7 scenes
+scenes = ["bicycle", "bonsai", "counter", "garden", "stump", "kitchen", "room"]
+
+result_dirs = ["results/benchmark_stmt"]
+# result_dirs = ["results/benchmark_antialiased_stmt"]
+# result_dirs = ["results/benchmark_mipsplatting_stmt"]
+
+all_metrics = {"psnr": [], "ssim": [], "lpips": [], "num_GS": []}
+print(result_dirs)
+
+for scene in scenes:
+    print(scene)
+    for result_dir in result_dirs:
+        for scale in ["8", "4", "2", "1"]:
+            json_files = glob.glob(f"{result_dir}/{scene}_{scale}/stats/val_step29999.json")
+            for json_file in json_files:    
+                data = json.load(open(json_file))
+                for k in ["psnr", "ssim", "lpips", "num_GS"]:
+                    all_metrics[k].append(data[k])
+                    print(f"{data[k]:.3f}", end=" ")
+                print()
+
+latex = []
+for k in ["psnr", "ssim", "lpips"]:
+    numbers = np.asarray(all_metrics[k]).reshape(-1, 4).mean(axis=0).tolist()
+    numbers = numbers + [np.mean(numbers)]
+    print(numbers)
+    if k == "psnr":
+        numbers = [f"{x:.2f}" for x in numbers]
+    else:
+        numbers = [f"{x:.3f}" for x in numbers]
+    latex.extend(numbers)
+print(" | ".join(latex))