SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.04890 · CVPR · 2024

A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals

Jingyi Yu, Ye Shi, Jingya Wang, Kaiyang Ji, Lan Xu, Jiangnan Tang

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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; 5 failures 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/2404.04890.json · badge: /api/ran/2404.04890.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
jn-tang/S2Fusion canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
create_conditioning_from_conf Ran
ran; our contract draft was wrong, not the code
jn-tang/S2Fusion/model/conditioning.py
code served (permissive licence) · get_code("1ce10587ab046d89")
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 Identity. 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
import torch.nn as nn
from omegaconf import DictConfig

torch.manual_seed(0)

# Create a minimal diffusion model
class MinimalDiffusion(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x):
        return self.linear(x)

# Create a minimal conditioning class that could be looked up in globals
class MockConditioning(nn.Module):
    def __init__(self, diffusion, smpl_path, **kwargs):
        super().__init__()
        self.diffusion = diffusion
        self.smpl_path = smpl_path
        self.kwargs = kwargs
    
    def forward(self, x):
        return x

# Register it in globals so it can be found
globals()['MockConditioning'] = MockConditioning

# Build the arguments
diffusion_model = MinimalDiffusion()
smpl_path = "/path/to/smpl/model.pkl"

# Create a DictConfig with a valid class name and args
conf = DictConfig({
    'cls': 'MockConditioning',
    'args': {
        'param1': 'value1',
        'param2': 42
    }
})

ARGS = {
    'diffusion': diffusion_model,
    'smpl_path': smpl_path,
    'conf': conf
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
omegaconf, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Identity — a Identity output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Identity 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
rot_mat_to_euler Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jn-tang/S2Fusion/model/SMPL/lbs.py
pointer only (licence: MIT); the stored copy get_code serves, from wjrzm/VP-MoCap, is pointer only (licence: NONE) · get_code("183c819df5293137")
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 wjrzm/VP-MoCap, 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.

sinusoidal_position_embedding Ran
ran; our contract draft was wrong, not the code
jn-tang/S2Fusion/model/backbone/embedding.py
code served (permissive licence) · get_code("00ccf5b4e0e83030")
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
from torch import nn
import math

torch.manual_seed(0)

# Create a small timesteps tensor (batch size 2)
timesteps = torch.tensor([0.0, 1.0], dtype=torch.float32)

# Define other parameters
dim_embedding = 4
scale = 1.0
period = 10000

# Map all parameters to their values
ARGS = {
    'timesteps': timesteps,
    'dim_embedding': dim_embedding,
    'scale': scale,
    'period': period
}
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
to_np Ran
ran; our contract draft was wrong, not the code
jn-tang/S2Fusion/model/SMPL/lbs.py
pointer only (licence: MIT); the stored copy get_code serves, from wjrzm/VP-MoCap, is pointer only (licence: NONE) · get_code("43ebe3b786b2d59b")
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 wjrzm/VP-MoCap, 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.

to_tensor Ran
ran; our contract draft was wrong, not the code
jn-tang/S2Fusion/model/SMPL/lbs.py
code served (permissive licence) · get_code("94904a5bd2e1074f")
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)

# Test case 1: numpy array
array_numpy = np.array([1.0, 2.0, 3.0, 4.0])

# Test case 2: python list
array_list = [1.0, 2.0, 3.0, 4.0]

# Test case 3: already a torch tensor (should not convert)
array_torch = torch.tensor([1.0, 2.0, 3.0, 4.0])

# Use the numpy array as the primary test case
ARGS = {
    "array": array_numpy,
    "dtype": torch.float32
}
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
create_loss_from_conf Not yet run
unverified (harvested, no recorded run)
jn-tang/S2Fusion/model/conditioning.py
code served (permissive licence) · get_code("88f252aa03d23f0b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 later) and 3 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
to_np 9 other papers
7 dated earlier, 2 later · 1 only as an assembly brick
2104.03953 (2021-04)
SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes
2112.07471 (2021-12)
I M Avatar: Implicit Morphable Head Avatars from Videos
2203.12575 (2022-03)
NeuMan: Neural Human Radiance Field from a Single Video
and 6 more not named here
to_tensor 6 other papers
4 dated earlier, 2 later
2104.03953 (2021-04)
SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes
2112.07471 (2021-12)
I M Avatar: Implicit Morphable Head Avatars from Videos
2307.13459 (2023-07)
Weakly-supervised 3D Pose Transfer with Keypoints
and 3 more not named here
rot_mat_to_euler 1 other paper
1 dated earlier
2403.17610 (2024-03)
MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors

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

Estimating full-body human motion via sparse tracking signals from head-mounted displays and hand controllers in 3D scenes is crucial to applications in AR/VR. One of the biggest challenges to this task is the one-to-many mapping from sparse observations to dense full-body motions, which endowed inherent ambiguities. To help resolve this ambiguous problem, we introduce a new framework to combine rich contextual information provided by scenes to benefit fullbody motion tracking from sparse observations. To estimate plausible human motions given sparse tracking signals and 3D scenes, we develop S 2 Fusion, a unified framework fusing Scene and sparse Signals with a conditional difFusion model. S 2 Fusion first extracts the spatial-temporal relations residing in the sparse signals via a periodic autoencoder, and then produces time-alignment feature embedding as additional inputs. Subsequently, by drawing initial noisy motion from a pre-trained prior, S 2 Fusion utilizes conditional diffusion to fuse scene geometry and sparse tracking signals to generate full-body scene-aware motions. The sampling procedure of S 2 Fusion is further guided by a specially designed scene-penetration loss and phase-matching loss, which effectively regularizes the motion of the lower body even in the absence of any tracking signals, making the generated motion much more plausible and coherent. Extensive experimental results have demonstrated that our S 2 Fusion outperforms the state-of-the-art in terms of estimation quality and smoothness. Code is available at https://github.com/jn-tang/S2Fusion.

For agents

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

get_harvested_code_for_paper("2404.04890")
get_code_for_paper("2404.04890")
have("2404.04890")

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

curl https://syntology.ai/api/ran/2404.04890.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.04890.svg)](https://syntology.ai/paper/2404.04890)

Connect an agent — have() is free.