SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.07531 · 2023

WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion

arXiv · PDF · Open in the Atlas

Code that ran

8 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; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 3 failures 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/2312.07531.json · badge: /api/ran/2312.07531.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
yohanshin/WHAM community (classifier label)
classifier basis not recorded on the link
8 ran · 4 no recorded run
FunctionStatusWhere it lives
bool_arg Ran
ran on a synthesized input
yohanshin/WHAM/configs/config.py
code served (permissive licence) · get_code("fe7aa89a39f9cc8b")
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 bool, 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)

ARGS = {
    'value': 'true'
}
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 bool, 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
compute_accel Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yohanshin/WHAM/lib/eval/eval_utils.py
code served (permissive licence) · get_code("58d59e9d2a8a0240")
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 1, dtype family float, shape (2,) 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

# Create a small sample joints array with shape (N, 25, 3)
# N=4 frames, 25 joints, 3 coordinates (x, y, z)
joints = np.random.randn(4, 25, 3).astype(np.float32)

ARGS = {
    "joints": joints
}
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 ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) 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
compute_error_accel Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yohanshin/WHAM/lib/eval/eval_utils.py
code served (permissive licence) · get_code("35c6e596e9bc4bb2")
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 1, dtype family float, shape (0,) 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

# Set random seed for reproducibility
np.random.seed(0)

# Create small test data
# N=5 frames, 14 joints, 3 coordinates (x, y, z)
N = 5
num_joints = 14
coord_dim = 3

joints_gt = np.random.randn(N, num_joints, coord_dim).astype(np.float32)
joints_pred = np.random.randn(N, num_joints, coord_dim).astype(np.float32)

# Create visibility array: N frames, with some invisible frames
vis = np.array([True, True, False, True, True], dtype=bool)

ARGS = {
    "joints_gt": joints_gt,
    "joints_pred": joints_pred,
    "vis": vis
}
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 ndarray, ndim 1, dtype family float, shape (0,) — shape (0,) 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
compute_error_verts Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yohanshin/WHAM/lib/eval/eval_utils.py
code served (permissive licence) · get_code("8e5bf3cf235ab46d")
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 1, dtype family float, shape (2,) 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)

# Create mock pred_verts: (batch_size=2, num_verts=6890, coords=3)
pred_verts = np.random.randn(2, 6890, 3).astype(np.float32)

# Create mock target_verts: (batch_size=2, num_verts=6890, coords=3)
target_verts = np.random.randn(2, 6890, 3).astype(np.float32)

# Create mock target_theta with proper shape
# target_theta should have shape (N, 82) where:
# - [:, :3] is global_orient
# - [:, 3:75] is body_pose (72 dims)
# - [:, 75:] is betas (10 dims for SMPL)
# Total: 3 + 72 + 10 = 85 dims (or 82 based on code: 3 + 72 + 7)
target_theta = np.random.randn(2, 82).astype(np.float32)

ARGS = {
    "pred_verts": pred_verts,
    "target_verts": target_verts,
    "target_theta": None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
lib, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) 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
extract_cam_param_xml Ran
ran on a synthesized input
yohanshin/WHAM/lib/data_utils/rich_eval_utils.py
code served (permissive licence) · get_code("869298cb3b9cfb7e")
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 torch
import xml.etree.ElementTree as ET
import tempfile
import os

torch.manual_seed(0)

# Create a temporary XML file with valid camera parameters
xml_content = """<?xml version="1.0"?>
<root>
    <CameraMatrix>
        <data>1.0 0.0 0.0 0.5 0.0 1.0 0.0 0.5 0.0 0.0 1.0 0.5</data>
    </CameraMatrix>
    <Intrinsics>
        <data>500.0 0.0 320.0 0.0 500.0 240.0 0.0 0.0 1.0</data>
    </Intrinsics>
</root>
"""

# Write to temporary file
temp_file = tempfile.NamedTemporaryFile(mode='w', suffix='.xml', delete=False)
temp_file.write(xml_content)
temp_file.close()

ARGS = {
    'xml_path': temp_file.name,
    'dtype': torch.float32
}
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 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
get_cfg Ran
ran on a synthesized input
yohanshin/WHAM/configs/config.py
code served (permissive licence) · get_code("2039dbb6edef87be")
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 CfgNode. 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 os
from yacs.config import CfgNode as CN

torch.manual_seed(0)

# Create a minimal args object that has the required attributes
class Args:
    def __init__(self):
        self.cfg = "/nonexistent/path/config.yaml"  # File doesn't exist, so won't be merged
        self.opts = []  # Empty opts list

args = Args()
test = False

ARGS = {
    "args": args,
    "test": test
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, yacs — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CfgNode — a CfgNode output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CfgNode 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
load_video Ran
ran on a synthesized input
yohanshin/WHAM/wham_api.py
code served (permissive licence) · get_code("f5e1eddc0f7791f2")
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, 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 cv2
import numpy as np
import tempfile
import os

# Create a temporary video file for testing
def create_test_video():
    temp_dir = tempfile.gettempdir()
    video_path = os.path.join(temp_dir, "test_video.mp4")
    
    # Create a simple video file using opencv
    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
    fps = 30
    width, height = 640, 480
    out = cv2.VideoWriter(video_path, fourcc, fps, (width, height))
    
    # Write a few frames
    for i in range(10):
        frame = np.random.randint(0, 256, (height, width, 3), dtype=np.uint8)
        out.write(frame)
    
    out.release()
    return video_path

video_file = create_test_video()

ARGS = {
    "video": video_file
}
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 tuple, ndim 1, dtype family float — a tuple 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
parse_args Ran
ran on a synthesized input
yohanshin/WHAM/configs/config.py
code served (permissive licence) · get_code("92381a84384aef12")
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, 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 argparse
from yacs.config import CfgNode as CN
import tempfile
import os

# Create a minimal config file for testing
cfg_content = """
EVAL: False
MODEL:
  NAME: 'test_model'
"""

# Create a temporary config file
temp_dir = tempfile.mkdtemp()
cfg_file_path = os.path.join(temp_dir, 'debug.yaml')
with open(cfg_file_path, 'w') as f:
    f.write(cfg_content)

# Set up the global cfg for get_cfg_defaults
cfg = CN()
cfg.EVAL = False
cfg.MODEL = CN()
cfg.MODEL.NAME = 'test_model'

ARGS = {
    'test': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yacs — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple 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
contact_loss Not yet run
unverified (harvested, no recorded run)
yohanshin/WHAM/lib/core/loss.py
code served (permissive licence) · get_code("e4d2ae7f674acab9")
How it ran

no invocation recorded.

full_projected_keypoint_loss Not yet run
unverified (harvested, no recorded run)
yohanshin/WHAM/lib/core/loss.py
code served (permissive licence) · get_code("cea0af0de65ed3e1")
How it ran

no invocation recorded.

is_dset Not yet run
unverified (harvested, no recorded run)
yohanshin/WHAM/lib/data_utils/emdb_eval_utils.py
code served (permissive licence) · get_code("d47bdae1805ba57f")
How it ran

no invocation recorded.

root_loss Not yet run
unverified (harvested, no recorded run)
yohanshin/WHAM/lib/core/loss.py
code served (permissive licence) · get_code("50063b39bbec654b")
How it ran

no invocation recorded.

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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 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
compute_accel 1 other paper
1 dated earlier
2308.10305 (2023-08)
Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video
compute_error_accel 1 other paper
1 dated earlier
2308.10305 (2023-08)
Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video
compute_error_verts 1 other paper
1 dated earlier
2308.10305 (2023-08)
Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video

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

The estimation of 3D human motion from video has progressed rapidly but current methods still have several key limitations. First, most methods estimate the human in camera coordinates. Second, prior work on estimating humans in global coordinates often assumes a flat ground plane and produces foot sliding. Third, the most accurate methods rely on computationally expensive optimization pipelines, limiting their use to offline applications. Finally, existing video-based methods are surprisingly less accurate than single-frame methods. We address these limitations with WHAM (World-grounded Humans with Accurate Motion), which accurately and efficiently reconstructs 3D human motion in a global coordinate system from video. WHAM learns to lift 2D keypoint sequences to 3D using motion capture data and fuses this with video features, integrating motion context and visual information. WHAM exploits camera angular velocity estimated from a SLAM method together with human motion to estimate the body's global trajectory. We combine this with a contact-aware trajectory refinement method that lets WHAM capture human motion in diverse conditions, such as climbing stairs. WHAM outperforms all existing 3D human motion recovery methods across multiple in-the-wild benchmarks. Code will be available for research purposes at http://wham.is.tue.mpg.de/

For agents

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

get_harvested_code_for_paper("2312.07531")
get_code_for_paper("2312.07531")
have("2312.07531")

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

curl https://syntology.ai/api/ran/2312.07531.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.07531.svg)](https://syntology.ai/paper/2312.07531)

Connect an agent — have() is free.