SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.04338 · 2024

Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion

arXiv · PDF · Open in the Atlas

Code that ran

4 of 8 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; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 1 failure of our instrument; 4 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/2406.04338.json · badge: /api/ran/2406.04338.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
liuff19/physics3d community (classifier label)
classifier basis not recorded on the link
4 ran · 4 no recorded run
FunctionStatusWhere it lives
C Ran
ran on a synthesized input
liuff19/physics3d/utils/threestudio_utils.py
code served (permissive licence) · get_code("d35b2c392fc4224e")
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 float, 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 torch
import numpy as np
from typing import Any

# Define a minimal config_to_primitive function since it's called in C()
def config_to_primitive(value: Any) -> Any:
    """Convert a config object to primitive types (list, dict, etc.)"""
    if isinstance(value, dict):
        return value
    elif hasattr(value, '__dict__'):
        return vars(value)
    elif isinstance(value, (list, tuple)):
        return list(value)
    return value

# Patch it into globals so C() can find it
import sys
current_module = sys.modules[__name__]
setattr(current_module, 'config_to_primitive', config_to_primitive)

# Test case 1: Simple numeric value
test1_value = 0.5
test1_epoch = 10
test1_global_step = 100

# Test case 2: List with 3 elements (will be prepended with 0)
# Format: [start_value, end_value, end_step] -> [0, start_value, end_value, end_step]
test2_value = [0.1, 0.9, 50]
test2_epoch = 5
test2_global_step = 25

# Test case 3: List with 4 elements using int end_step (uses global_step)
test3_value = [10, 0.01, 0.1, 100]
test3_epoch = 0
test3_global_step = 50

# Test case 4: List with 4 elements using float end_step (uses epoch)
test4_value = [0, 0.5, 2.0, 10.0]
test4_epoch = 5
test4_global_step = 0

# Create a stand-in config class that can be converted to a list
class ConfigScalar:
    def __init__(self, values):
        self.values = values
    
    def __iter__(self):
        return iter(self.values)

ARGS = {
    "value": test2_value,
    "epoch": 5,
    "global_step": 25
}
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 float, ndim 0, dtype family float — no output shape is stated: observe_signature.py could not observe it (fixture:KeyError)
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
generate_local_coord Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
liuff19/physics3d/utils/camera_view_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from tyhuang0428/dreamphysics, is pointer only (licence: NONE) · get_code("ddd567b7a94424d3")
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 tyhuang0428/dreamphysics, 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.

parse_version Ran
ran on a synthesized input
liuff19/physics3d/utils/threestudio_utils.py
code served (permissive licence) · get_code("6af3c658eeadc4ad")
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 Version. 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 torch
from packaging import version

ARGS = {
    "ver": "1.2.3"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
packaging, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Version — a Version output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Version output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
shifted_expotional_decay Ran
ran on a synthesized input
liuff19/physics3d/utils/threestudio_utils.py
code served (permissive licence) · get_code("6295df114ab36436")
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)

# Parameters for shifted_expotional_decay
a = torch.tensor([[1.0, 2.0, 3.0, 4.0],
                   [5.0, 6.0, 7.0, 8.0]])  # shape (2, 4)

b = torch.tensor([[0.1, 0.2, 0.3, 0.4],
                   [0.15, 0.25, 0.35, 0.45]])  # shape (2, 4)

c = torch.tensor([[0.5, 0.6, 0.7, 0.8],
                   [0.9, 1.0, 1.1, 1.2]])  # shape (2, 4)

r = torch.tensor([[1.0, 2.0, 3.0, 4.0],
                   [5.0, 6.0, 7.0, 8.0]])  # shape (2, 4)

ARGS = {
    'a': a,
    'b': b,
    'c': c,
    'r': r
}
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
decode_param_json Not yet run
unverified (harvested, no recorded run)
liuff19/physics3d/utils/decode_param.py
code served (permissive licence) · get_code("43490c98175d772f")
How it ran

no invocation recorded.

find_far_points Not yet run
unverified (harvested, no recorded run)
liuff19/physics3d/utils/decode_param.py
code served (permissive licence) · get_code("0554248af1b5ef2f")
How it ran

no invocation recorded.

generate_camera_rotation_matrix Not yet run
unverified (harvested, no recorded run)
liuff19/physics3d/utils/camera_view_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from tyhuang0428/dreamphysics, is pointer only (licence: NONE) · get_code("2b9cf8baab6bc8b4")
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 tyhuang0428/dreamphysics, 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. No invocation recorded.

get_point_on_sphere Not yet run
unverified (harvested, no recorded run)
liuff19/physics3d/utils/camera_view_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from tyhuang0428/dreamphysics, is pointer only (licence: NONE) · get_code("fc9200f0d0d5f797")
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 tyhuang0428/dreamphysics, 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. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 3 the same month, 0 later) and 5 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
generate_camera_rotation_matrix 1 other paper
1 the same month
2406.01476 (2024-06)
DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors
generate_local_coord 1 other paper
1 the same month
2406.01476 (2024-06)
DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors
get_point_on_sphere 1 other paper
1 the same month
2406.01476 (2024-06)
DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors

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

In recent years, there has been rapid development in 3D generation models, opening up new possibilities for applications such as simulating the dynamic movements of 3D objects and customizing their behaviors. However, current 3D generative models tend to focus only on surface features such as color and shape, neglecting the inherent physical properties that govern the behavior of objects in the real world. To accurately simulate physics-aligned dynamics, it is essential to predict the physical properties of materials and incorporate them into the behavior prediction process. Nonetheless, predicting the diverse materials of real-world objects is still challenging due to the complex nature of their physical attributes. In this paper, we propose \textbf{Physics3D}, a novel method for learning various physical properties of 3D objects through a video diffusion model. Our approach involves designing a highly generalizable physical simulation system based on a viscoelastic material model, which enables us to simulate a wide range of materials with high-fidelity capabilities. Moreover, we distill the physical priors from a video diffusion model that contains more understanding of realistic object materials. Extensive experiments demonstrate the effectiveness of our method with both elastic and plastic materials. Physics3D shows great potential for bridging the gap between the physical world and virtual neural space, providing a better integration and application of realistic physical principles in virtual environments. Project page: https://liuff19.github.io/Physics3D.

For agents

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

get_harvested_code_for_paper("2406.04338")
get_code_for_paper("2406.04338")
have("2406.04338")

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

curl https://syntology.ai/api/ran/2406.04338.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.04338.svg)](https://syntology.ai/paper/2406.04338)

Connect an agent — have() is free.