SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.13648 · 2024

V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians

arXiv · PDF · Open in the Atlas

Code that ran

12 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2409.13648.json · badge: /api/ran/2409.13648.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
AuthorityWang/VideoGS community (classifier label)
classifier basis not recorded on the link
12 ran · 1 no recorded run
FunctionStatusWhere it lives
denormalize_uint16 Ran
ran on a synthesized input
AuthorityWang/VideoGS/compress/decompress_video_2_ckpt.py
code served (permissive licence) · get_code("1cb7499d7671fea8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family float, shape (4,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function denormalize_uint16 takes three parameters:
# - data: should be a tensor or array with normalized uint16 values (0 to 2^16-1)
# - min_val: the minimum value for denormalization (scalar)
# - max_val: the maximum value for denormalization (scalar)

# Create a small normalized uint16 data tensor (values between 0 and 2^16-1)
data = torch.tensor([0, 16383, 32767, 65535], dtype=torch.float32)

# Set min and max values for denormalization
min_val = -1.0
max_val = 1.0

ARGS = {
    "data": data,
    "min_val": min_val,
    "max_val": max_val,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (4,) — shape (4,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
denormalize_uint8 Ran
ran on a synthesized input
AuthorityWang/VideoGS/compress/decompress_video_2_ckpt.py
code served (permissive licence) · get_code("7dd44bb86b47efb6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function denormalize_uint8 takes:
# - data: array-like of uint8 values (0-255)
# - min_val: scalar minimum value for denormalization
# - max_val: scalar maximum value for denormalization
# It performs: data / 255.0 * (max_val - min_val) + min_val

# Create a small uint8 tensor with values in range [0, 255]
data = torch.randint(0, 256, (2, 4), dtype=torch.uint8)

# Create scalar min and max values
min_val = -1.0
max_val = 1.0

ARGS = {
    "data": data,
    "min_val": min_val,
    "max_val": max_val
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
entropy_regularization_loss Ran
ran on a synthesized input
AuthorityWang/VideoGS/train_dynamic.py
code served (permissive licence) · get_code("e31a9ca5ec35e095")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)
np.random.seed(0)

class GaussianStandIn:
    """Stand-in Gaussian class with required attributes."""
    def __init__(self, num_points, scaling_dim, rotation_dim, opacity_dim):
        self._scaling = torch.randn(num_points, scaling_dim)
        self._rotation = torch.randn(num_points, rotation_dim)
        self._opacity = torch.randn(num_points, opacity_dim)

num_points = 2
scaling_dim = 3
rotation_dim = 4
opacity_dim = 1

current_frame_gaussian = GaussianStandIn(num_points, scaling_dim, rotation_dim, opacity_dim)
last_frame_gaussian = GaussianStandIn(num_points, scaling_dim, rotation_dim, opacity_dim)

ARGS = {
    'current_frame_gaussian': current_frame_gaussian,
    'last_frame_gaussian': last_frame_gaussian,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
gaussian Ran
ran, honoured the contract we drafted
AuthorityWang/VideoGS/utils/loss_utils.py
code served (permissive licence) · get_code("c56b7ef16f309a45")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 1, dtype family float, shape (5,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from math import exp

torch.manual_seed(0)

ARGS = {
    "window_size": 5,
    "sigma": 1.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (5,) — shape (5,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_attribute Ran
ran on a synthesized input
AuthorityWang/VideoGS/prune_gaussian.py
code served (permissive licence) · get_code("87f73e8bf0b19ac0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function get_attribute takes a single parameter: sh_degree
# It's an integer that controls the spherical harmonics degree
# Looking at the function body, sh_degree is used in arithmetic operations
# to compute frest_dim and generate attribute names

sh_degree = 2

ARGS = {
    'sh_degree': sh_degree
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_ply_matrix Ran
ran on a synthesized input
AuthorityWang/VideoGS/prune_gaussian.py
code served (permissive licence) · get_code("154f4c361d622201")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from plyfile import PlyData, PlyElement
import tempfile
import os

# Create a temporary PLY file for testing
temp_dir = tempfile.mkdtemp()
temp_ply_path = os.path.join(temp_dir, "test.ply")

# Create vertex data with multiple attributes
vertex_data = np.array([
    (0.0, 1.0, 2.0, 3.0),
    (4.0, 5.0, 6.0, 7.0),
], dtype=[('x', 'f4'), ('y', 'f4'), ('z', 'f4'), ('w', 'f4')])

# Create PLY element and file
vertex_element = PlyElement.describe(vertex_data, 'vertex')
ply_file = PlyData([vertex_element])
ply_file.write(temp_ply_path)

ARGS = {
    'file_path': temp_ply_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, plyfile — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
l1_loss Ran
ran; our contract draft was wrong, not the code
AuthorityWang/VideoGS/utils/loss_utils.py
code served (permissive licence) · get_code("ac0e42d6fbcfbbe6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small tensors for network output and ground truth
# Both should have the same shape for the subtraction and mean operations
network_output = torch.randn(2, 4)  # batch size 2, 4 dimensions
gt = torch.randn(2, 4)  # batch size 2, 4 dimensions

ARGS = {
    "network_output": network_output,
    "gt": gt,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
l2_loss Ran
ran, honoured the contract we drafted
AuthorityWang/VideoGS/utils/loss_utils.py
code served (permissive licence) · get_code("8c3b0f873ba11813")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create small tensors for network output and ground truth
# Both should have the same shape for the loss computation
# Using batch size 2, feature dimension 4
network_output = torch.randn(2, 4)
gt = torch.randn(2, 4)

ARGS = {
    "network_output": network_output,
    "gt": gt,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
normalize_uint16 Ran
ran on a synthesized input
AuthorityWang/VideoGS/compress/compress_ckpt_2_image.py
code served (permissive licence) · get_code("96e623af5b067403")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create sample uint16 data
data = np.array([100, 500, 1000, 5000, 10000, 20000, 30000, 50000], dtype=np.uint16)

ARGS = {
    "data": data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
normalize_uint8 Ran
ran on a synthesized input
AuthorityWang/VideoGS/compress/compress_ckpt_2_image.py
code served (permissive licence) · get_code("fc6fcf7c1438e113")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create sample uint8 data with a range of values
data = np.array([
    [10, 50, 100, 200],
    [30, 75, 150, 255]
], dtype=np.uint8)

ARGS = {
    "data": data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
normalize_uint8_tog Ran
ran on a synthesized input
AuthorityWang/VideoGS/compress/compress_ckpt_2_image.py
code served (permissive licence) · get_code("bc0ca979e779a1a6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create sample data as a numpy array
data = np.array([0, 50, 100, 150, 200, 255], dtype=np.float32)

# Define min and max values for normalization
min_val = 0.0
max_val = 255.0

ARGS = {
    "data": data,
    "min_val": min_val,
    "max_val": max_val
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
read_video Ran
ran on a synthesized input
AuthorityWang/VideoGS/compress/decompress_video_2_ckpt.py
code served (permissive licence) · get_code("a52be4820c08e12e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 3, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import cv2
import numpy as np
import tempfile
import os

# Create a temporary video file for testing
def create_test_video(path, num_frames=5, width=320, height=240):
    """Create a simple test video file"""
    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
    out = cv2.VideoWriter(path, fourcc, 20.0, (width, height))
    
    for i in range(num_frames):
        # Create a simple frame with changing content
        frame = np.zeros((height, width, 3), dtype=np.uint8)
        frame[:, :] = (i * 50) % 256
        # Add some variation
        frame[50:100, 50:100] = (i * 100) % 256
        out.write(frame)
    
    out.release()

# Create temporary video file
temp_dir = tempfile.gettempdir()
video_path = os.path.join(temp_dir, "test_video.mp4")
create_test_video(video_path, num_frames=3, width=320, height=240)

ARGS = {
    "video_path": video_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 3, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
prepare_output_and_logger Not yet run
unverified (harvested, no recorded run)
AuthorityWang/VideoGS/train_dynamic.py
pointer only (licence: MIT); the stored copy get_code serves, from kornelhowil/CLIPGaussian, is pointer only (licence: NOASSERTION) · get_code("74c6a993a0948239")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from kornelhowil/CLIPGaussian, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 4 later) and 9 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
gaussian 160 other papers
116 dated earlier, 1 the same month, 42 later, 1 same year, order not determinable · 7 only as an assembly brick
1812.11941 (2018-12)
High Quality Monocular Depth Estimation via Transfer Learning
1904.01538 (2019-04)
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
1907.11628 (2019-07)
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
and 157 more not named here
l1_loss 93 other papers
56 dated earlier, 1 the same month, 36 later
2308.04079 (2023-08)
3D Gaussian Splatting for Real-Time Radiance Field Rendering
2309.13101 (2023-09)
Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction
2310.08528 (2023-10)
4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
and 90 more not named here
l2_loss 90 other papers
54 dated earlier, 1 the same month, 35 later
2308.04079 (2023-08)
3D Gaussian Splatting for Real-Time Radiance Field Rendering
2309.13101 (2023-09)
Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction
2310.08528 (2023-10)
4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
and 87 more not named here
prepare_output_and_logger 15 other papers
8 dated earlier, 7 later
2309.13101 (2023-09)
Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction
2311.18159 (2023-11)
CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization
2312.16812 (2023-12)
Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis
and 12 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Experiencing high-fidelity volumetric video as seamlessly as 2D videos is a long-held dream. However, current dynamic 3DGS methods, despite their high rendering quality, face challenges in streaming on mobile devices due to computational and bandwidth constraints. In this paper, we introduce V^3 (Viewing Volumetric Videos), a novel approach that enables high-quality mobile rendering through the streaming of dynamic Gaussians. Our key innovation is to view dynamic 3DGS as 2D videos, facilitating the use of hardware video codecs. Additionally, we propose a two-stage training strategy to reduce storage requirements with rapid training speed. The first stage employs hash encoding and shallow MLP to learn motion, then reduces the number of Gaussians through pruning to meet the streaming requirements, while the second stage fine tunes other Gaussian attributes using residual entropy loss and temporal loss to improve temporal continuity. This strategy, which disentangles motion and appearance, maintains high rendering quality with compact storage requirements. Meanwhile, we designed a multi-platform player to decode and render 2D Gaussian videos. Extensive experiments demonstrate the effectiveness of V^3, outperforming other methods by enabling high-quality rendering and streaming on common devices, which is unseen before. As the first to stream dynamic Gaussians on mobile devices, our companion player offers users an unprecedented volumetric video experience, including smooth scrolling and instant sharing. Our project page with source code is available at https://authoritywang.github.io/v3/.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2409.13648")
get_code_for_paper("2409.13648")
have("2409.13648")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2409.13648.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2409.13648.svg)](https://syntology.ai/paper/2409.13648)

Connect an agent — have() is free.