SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.07795 · NeurIPS · 2024

Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos

Bastian Wandt, Cuong Le, Viktor Johansson, Manon Kok

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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 0 have no contract verdict; 2 failures of our instrument; 2 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/2410.07795.json · badge: /api/ran/2410.07795.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
cuongle1206/OSDCap canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
cuongle1206/osdcap marked official in Papers with Code
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
data_mapping_h36m Ran
ran; our contract draft was wrong, not the code
cuongle1206/OSDCap/data_gen.py
code served (permissive licence) · get_code("5831dbe57bace921")
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 2, dtype family float, shape (2, 67) 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)

# Analyze the function:
# - root_trans: tensor, used in torch.cat, shape (length, ?)
# - root_rot: tensor, used with slicing [:, 1:] and [:, 0:1], shape (length, ?)
# - joint_angle: tensor, indexed as [:, h36m_id[j], :], shape (length, 22, 3) at minimum
# - length: int, used for torch.zeros and reshape
# - qsize: int, appears to be unused in the function body

length = 2
qsize = 5

# root_trans: shape (length, 3) - 3D translation
root_trans = torch.randn(length, 3)

# root_rot: shape (length, 4) - quaternion or 4D rotation representation
# Used as root_rot[:, 1:] (shape length, 3) and root_rot[:, 0:1] (shape length, 1)
root_rot = torch.randn(length, 4)

# joint_angle: shape (length, 22, 3)
# Needs at least 22 joints to accommodate max(h36m_id) = 21
joint_angle = torch.randn(length, 22, 3)

ARGS = {
    "root_trans": root_trans,
    "root_rot": root_rot,
    "joint_angle": joint_angle,
    "length": length,
    "qsize": qsize,
}
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, 67) — shape (2, 67) 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
data_mapping_smpl Ran
ran; our contract draft was wrong, not the code
cuongle1206/OSDCap/data_gen.py
code served (permissive licence) · get_code("6eac619ccbda2161")
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 2, dtype family float, shape (2, 67) 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)

# Analyze the function:
# - root_trans: indexed with [:, ...], concatenated, shape (length, ...)
# - root_rot: indexed with [:, 1:], [:, 0:1], shape (length, ...)
# - joint_angle: indexed with [:, smpl_id[j], :], shape (length, 21, 3)
# - length: used in range and tensor creation
# - qsize: not used in the function body

length = 2
batch_size = length

# root_trans: (length, 3) - root translation
root_trans = torch.randn(length, 3)

# root_rot: (length, 4) - root rotation (quaternion or similar, needs at least 4 dims for [:, 1:] and [:, 0:1])
root_rot = torch.randn(length, 4)

# joint_angle: (length, 21, 3) - 21 joints with 3D angles
# smpl_id has 20 elements, max index is 20, so we need at least 21 joints
joint_angle = torch.randn(length, 21, 3)

# qsize: not used in function, can be any value
qsize = 5

ARGS = {
    "root_trans": root_trans,
    "root_rot": root_rot,
    "joint_angle": joint_angle,
    "length": length,
    "qsize": qsize,
}
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, 67) — shape (2, 67) 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
OSDNet Not yet run
unverified (harvested, no recorded run)
cuongle1206/osdcap/common/networks.py
code served (permissive licence) · get_code("eaa3503f1f5fca94")
How it ran

no invocation recorded.

get_contact_labels Not yet run
unverified (harvested, no recorded run)
cuongle1206/OSDCap/data_gen.py
code served (permissive licence) · get_code("8d38ec37a70b0ec6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

Figure 1: OSDCap is an optimal-state dynamics estimation (cyan) based on two streams of input motion, a kinematics-based pose estimation from videos (top-left), and a physics-based simulation by a meta-PD controller (bottom-left). The predicted motion is physically-plausible, contains reduced high-frequency noise, while retaining highly accurate global position.

For agents

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

get_harvested_code_for_paper("2410.07795")
get_code_for_paper("2410.07795")
have("2410.07795")

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

curl https://syntology.ai/api/ran/2410.07795.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.07795.svg)](https://syntology.ai/paper/2410.07795)

Connect an agent — have() is free.