SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.14937 · 2023

SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes

arXiv · PDF · Open in the Atlas

Code that ran

12 of 12 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; 4 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2312.14937.json · badge: /api/ran/2312.14937.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
yihua7/SC-GS canonical (classifier label)
classifier basis: census
12 ran · 0 no recorded run
FunctionStatusWhere it lives
quaternion_multiply Ran
ran; our contract draft was wrong, not the code
yihua7/SC-GS/scene/gaussian_model.py
code served (permissive licence) · get_code("90ed0313f554ec45")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) 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. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:58:55Z). 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 two quaternion tensors
# Shape: (batch_size, 4) where 4 represents [w, x, y, z]
q1 = torch.randn(2, 4)
q2 = torch.randn(2, 4)

ARGS = {
    "q1": q1,
    "q2": q2,
}
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 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
dot Ran
ran, honoured the contract we drafted
yihua7/SC-GS/cam_utils.py
code served (permissive licence) · get_code("e35aafbf0069edb6")
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, 1) 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
import torch

torch.manual_seed(0)

# Test with numpy arrays
x_np = np.random.randn(2, 4).astype(np.float32)
y_np = np.random.randn(2, 4).astype(np.float32)

# Test with torch tensors
x_torch = torch.randn(2, 4)
y_torch = torch.randn(2, 4)

# We'll use torch tensors for the main ARGS
ARGS = {
    "x": x_torch,
    "y": y_torch
}
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, 1) — shape (2, 1) 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
getProjectionMatrix Ran
ran, honoured the contract we drafted
yihua7/SC-GS/edit_gui.py
code served (permissive licence) · get_code("a148f7f80321414f")
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 (4, 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 math

torch.manual_seed(0)

# Parameters for a typical perspective projection matrix
# znear and zfar define the near and far clipping planes
# fovX and fovY define the field of view angles in radians

ARGS = {
    "znear": 0.1,
    "zfar": 100.0,
    "fovX": math.pi / 4,  # 45 degrees in radians
    "fovY": math.pi / 4,  # 45 degrees in radians
}
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 2, dtype family float, shape (4, 4) — shape (4, 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
getWorld2View2 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yihua7/SC-GS/edit_gui.py
pointer only (licence: MIT); the stored copy get_code serves, from RockyXu66/splatbus, is pointer only (licence: NONE) · get_code("ddab833907fa5d71")
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 RockyXu66/splatbus, and GitHub detected no licence in that repository when it was checked. 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. A run is recorded.

landmark_interpolate Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yihua7/SC-GS/train_gui.py
code served (permissive licence) · get_code("919b604b3c2ecfbc")
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 float64, ndim 0, 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 numpy as np

ARGS = {
    'landmarks': np.array([0.1, 0.5, 2.0, 5.0]),
    'steps': np.array([0, 100, 500, 1000]),
    'step': 250,
    'interpolation': 'log'
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
length Ran
ran, honoured the contract we drafted
yihua7/SC-GS/cam_utils.py
code served (permissive licence) · get_code("43cdc168f88caf9b")
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, 1) 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
import torch

torch.manual_seed(0)

# Test with a torch tensor
x_torch = torch.randn(2, 4)

# Test with a numpy array
x_numpy = np.random.randn(2, 4)

# The function signature is: def length(x, eps=1e-20)
# It uses x to compute dot products and sqrt
# eps is used as a minimum clamp value

ARGS = {
    "x": x_torch,
    "eps": 1e-20
}
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, 1) — shape (2, 1) 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
matrix_to_quaternion Ran
ran; our contract draft was wrong, not the code
yihua7/SC-GS/edit_gui.py
code served (permissive licence) · get_code("b537e6550dc72705")
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

torch.manual_seed(0)

# Create a valid rotation matrix (3x3) in a batch
# A proper rotation matrix is orthogonal with determinant 1
# We'll create a simple batch of 2 rotation matrices

# Identity rotation matrix
identity = torch.eye(3, dtype=torch.float32)

# Create a simple rotation matrix (90 degrees around z-axis)
angle = torch.tensor(3.14159265 / 2)  # 90 degrees
c = torch.cos(angle)
s = torch.sin(angle)
rotation_z = torch.tensor([
    [c, -s, 0],
    [s, c, 0],
    [0, 0, 1]
], dtype=torch.float32)

# Stack them into a batch of shape (2, 3, 3)
matrix = torch.stack([identity, rotation_z], dim=0)

ARGS = {
    'matrix': matrix
}
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 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
quaternion_multiply Ran
ran; our contract draft was wrong, not the code
yihua7/SC-GS/lap_deform.py
code served (permissive licence) · get_code("91aa696a54521854")
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

torch.manual_seed(0)

# Create two quaternion tensors with shape (2, 4)
# Quaternions are represented as [w, x, y, z]
a = torch.randn(2, 4)
b = torch.randn(2, 4)

ARGS = {
    "a": a,
    "b": b,
}
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 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
quaternion_raw_multiply Ran
ran; our contract draft was wrong, not the code
yihua7/SC-GS/lap_deform.py
code served (permissive licence) · get_code("0a2929fc0a4c725c")
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

torch.manual_seed(0)

# Create two small quaternion tensors
# Shape: (batch_size, 4) where the last dimension is [w, x, y, z]
a = torch.randn(2, 4)
b = torch.randn(2, 4)

ARGS = {
    "a": a,
    "b": b,
}
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 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
readImages Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yihua7/SC-GS/metrics.py
code served (permissive licence) · get_code("cdd00787894554b5")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 os
import tempfile
from pathlib import Path
from PIL import Image
import torch
import numpy as np

torch.manual_seed(0)

# Create temporary directories with dummy image files
temp_renders_dir = tempfile.mkdtemp()
temp_gt_dir = tempfile.mkdtemp()

renders_dir = Path(temp_renders_dir)
gt_dir = Path(temp_gt_dir)

# Create 2 small dummy images (4x3 RGB)
for i in range(2):
    # Create render image
    render_array = np.random.randint(0, 256, (3, 4, 3), dtype=np.uint8)
    render_img = Image.fromarray(render_array.transpose(1, 2, 0), mode='RGB')
    render_img.save(renders_dir / f"render_{i}.png")
    
    # Create ground truth image
    gt_array = np.random.randint(0, 256, (3, 4, 3), dtype=np.uint8)
    gt_img = Image.fromarray(gt_array.transpose(1, 2, 0), mode='RGB')
    gt_img.save(gt_dir / f"render_{i}.png")

ARGS = {
    "renders_dir": renders_dir,
    "gt_dir": gt_dir,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — 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
safe_normalize Ran
ran, honoured the contract we drafted
yihua7/SC-GS/cam_utils.py
code served (permissive licence) · get_code("8a8484ccf552d87f")
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)

# safe_normalize takes one required parameter: x
# It can be either a numpy array or a torch tensor
# The function uses x in division and passes it to length()
# length() computes x * x and sums over the last dimension

# Create a small torch tensor (batch=2, dim=4)
x_torch = torch.randn(2, 4)

# Also create a numpy equivalent for testing flexibility
x_numpy = np.random.randn(2, 4).astype(np.float32)

# The function can work with either, so we'll use torch
ARGS = {
    "x": x_torch
}
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
standardize_quaternion Ran
ran; our contract draft was wrong, not the code
yihua7/SC-GS/lap_deform.py
code served (permissive licence) · get_code("8a3c7819836cbb9a")
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

torch.manual_seed(0)

# The function takes a tensor of quaternions and standardizes them
# by ensuring the first component (index 0) is non-negative.
# It expects a tensor of shape (..., 4) where the last dimension is 4 (quaternion components)

quaternions = torch.randn(2, 4)

ARGS = {
    "quaternions": quaternions
}
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 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

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 8 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 5 the same month, 8 later) and 4 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
readImages 54 other papers
6 dated earlier, 4 the same month, 44 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 51 more not named here
dot 8 other papers
2 dated earlier, 1 the same month, 5 later
2311.17061 (2023-11)
HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
2311.17082 (2023-11)
DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling
2312.13271 (2023-12)
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
and 5 more not named here
getWorld2View2 8 other papers
2 the same month, 6 later
2312.02155 (2023-12)
GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis
2312.09147 (2023-12)
Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers
2403.16095 (2024-03)
CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field
and 5 more not named here
length 8 other papers
2 dated earlier, 1 the same month, 5 later
2311.17061 (2023-11)
HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
2311.17082 (2023-11)
DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling
2312.13271 (2023-12)
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
and 5 more not named here
safe_normalize 8 other papers
2 dated earlier, 1 the same month, 5 later
2311.17061 (2023-11)
HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
2311.17082 (2023-11)
DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling
2312.13271 (2023-12)
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
and 5 more not named here
getProjectionMatrix 3 other papers
1 dated earlier, 2 later
2309.13101 (2023-09)
Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction
2406.17601 (2024-06)
Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
2411.19290 (2024-11)
TRASE: Tracking-free 4D Segmentation and Editing
quaternion_multiply 2 other papers
2 later
2406.03697 (2024-06)
Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction
2506.07865 (2025-06)
FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity
landmark_interpolate 1 other paper
1 later
2411.19290 (2024-11)
TRASE: Tracking-free 4D Segmentation and Editing

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

Novel view synthesis for dynamic scenes is still a challenging problem in computer vision and graphics. Recently, Gaussian splatting has emerged as a robust technique to represent static scenes and enable high-quality and real-time novel view synthesis. Building upon this technique, we propose a new representation that explicitly decomposes the motion and appearance of dynamic scenes into sparse control points and dense Gaussians, respectively. Our key idea is to use sparse control points, significantly fewer in number than the Gaussians, to learn compact 6 DoF transformation bases, which can be locally interpolated through learned interpolation weights to yield the motion field of 3D Gaussians. We employ a deformation MLP to predict time-varying 6 DoF transformations for each control point, which reduces learning complexities, enhances learning abilities, and facilitates obtaining temporal and spatial coherent motion patterns. Then, we jointly learn the 3D Gaussians, the canonical space locations of control points, and the deformation MLP to reconstruct the appearance, geometry, and dynamics of 3D scenes. During learning, the location and number of control points are adaptively adjusted to accommodate varying motion complexities in different regions, and an ARAP loss following the principle of as rigid as possible is developed to enforce spatial continuity and local rigidity of learned motions. Finally, thanks to the explicit sparse motion representation and its decomposition from appearance, our method can enable user-controlled motion editing while retaining high-fidelity appearances. Extensive experiments demonstrate that our approach outperforms existing approaches on novel view synthesis with a high rendering speed and enables novel appearance-preserved motion editing applications. Project page: https://yihua7.github.io/SC-GS-web/

For agents

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

get_harvested_code_for_paper("2312.14937")
get_code_for_paper("2312.14937")
have("2312.14937")

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

curl https://syntology.ai/api/ran/2312.14937.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.14937.svg)](https://syntology.ai/paper/2312.14937)

Connect an agent — have() is free.