SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.12959 · ECCV · 2024

WHAC: World-grounded Humans and Cameras

Ziwei Liu, Zhongang Cai, Lei Yang, Chen Wei, Haiyi Mei, Zhitao Yang, Wanqi Yin ⋆, Ruisi Wang, Fanzhou Wang, Weiye Xiao, Qingping Sun, Atsushi Yamashita

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 (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 3 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/2403.12959.json · badge: /api/ran/2403.12959.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
openxrlab/xrfeitoria marked official in Papers with Code
Papers with Code archive
5 ran · 1 no recorded run
FunctionStatusWhere it lives
ConverterMotion Ran
ran on a synthesized input
openxrlab/xrfeitoria/xrfeitoria/utils/anim/motion.py
code served (permissive licence) · get_code("bbd8dde388504803")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned ndarray, ndim 2, 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

class ConverterMotion:

    @classmethod
    def vec_humandata2smplx(cls, vector: np.ndarray) -> np.ndarray:
        """From humandata transl (in **OpenCV space**) to SMPLX armature's **pelvis
        local space** in Blender. (The pelvis local space is designed to be the same
        with **SMPL space**.)

        [right, front, up]: (-x, -z, -y) ==> (-x, z, y)

        Args:
            vector (np.ndarray): of shape (N, 3) or (3,)

        Returns:
            np.ndarray: of shape (N, 3) or (3,)
        """
        if isinstance(vector, (list, tuple)):
            vector = np.array(vector)
        if vector.shape == (3,):
            ret = np.array([vector[0], -vector[1], -vector[2]], dtype=vector.dtype)
        elif vector.ndim == 2 and vector.shape[1] == 3:
            ret = np.array([vector[:, 0], -vector[:, 1], -vector[:, 2]]).T
        else:
            raise ValueError(f'vector.shape={vector.shape}')
        return ret

    @classmethod
    def vec_smplx2humandata(cls, vector: np.ndarray) -> np.ndarray:
        return cls.vec_humandata2smplx(vector)

    @classmethod
    def vec_amass2humandata(cls, vector: np.ndarray) -> np.ndarray:
        """From amass transl (pelvis's local space) to humandata transl (in **OpenCV
        space**)

        [right, front, up]: (x, y, z) ==> (-x, -z, -y)

        (CAUTION: we can see amass animation actors face back
            in blender via the smplx add-on)

        Args:
            vector (np.ndarray): of shape (N, 3) or (3,)

        Returns:
            np.ndarray: of shape (N, 3) or (3,)
        """
        if isinstance(vector, (list, tuple)):
            vector = np.array(vector)
        if vector.shape == (3,):
            vector = np.array([-vector[0], -vector[2], -vector[1]], dtype=vector.dtype)
        elif vector.ndim == 2 and vector.shape[1] == 3:
            vector = np.array([-vector[:, 0], -vector[:, 2], -vector[:, 1]]).T
        else:
            raise ValueError(f'vector.shape={vector.shape}')
        return vector


INIT_ARGS = {}

ARGS = {
    'vector': np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
}

METHOD = 'vec_humandata2smplx'

instance = ConverterMotion()
result = getattr(instance, METHOD)(**ARGS)
print(result)
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 2, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
Motion Ran
ran on a synthesized input · constructed an object; no result was computed
openxrlab/xrfeitoria/xrfeitoria/utils/anim/motion.py
code served (permissive licence) · get_code("c205e6610a316d8e")
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 an instance of its own class, Motion: the run constructed the object and did not call it, so no result was computed. 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 numpy as np

# Create valid arguments for Motion.__init__
# The function expects:
# - transl: np.ndarray that will be reshaped to [-1, 3]
# - body_poses: np.ndarray that will be reshaped to [frames, -1, 3]
# - n_frames: Optional[int]
# - fps: float

# Create small motion data
n_frames = 2
n_bones = 4

# transl shape: (n_frames, 3) - translation data for root bone
transl = np.random.randn(n_frames, 3).astype(np.float32)

# body_poses shape: (n_frames, n_bones, 3) - rotation vectors for each bone
body_poses = np.random.randn(n_frames, n_bones, 3).astype(np.float32)

# fps value
fps = 30.0

ARGS = {
    "transl": transl,
    "body_poses": body_poses,
    "n_frames": n_frames,
    "fps": fps,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Motion — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Motion 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
_get_from_smpl_x_ Ran
ran; our contract draft was wrong, not the code
openxrlab/xrfeitoria/xrfeitoria/utils/anim/motion.py
code served (permissive licence) · get_code("4fc389d3c05627f8")
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 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 numpy as np

# Create a small SMPL-X data dict with sample data
n_frames = 2
n_dims = 4

smpl_x_data = {
    'pose': np.random.randn(n_frames * n_dims).astype(np.float32),
    'shape': np.random.randn(n_frames * 10).astype(np.float32),
    'empty_key': np.array([]),
}

ARGS = {
    'key': 'pose',
    'shape': (n_frames, n_dims),
    'smpl_x_data': smpl_x_data,
    'dtype': np.float32,
    'required': True,
}
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 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
_transform_transl_global_orient_ Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
openxrlab/xrfeitoria/xrfeitoria/utils/anim/motion.py
code served (permissive licence) · get_code("0945df8ecf2bd69c")
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 3, 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
from scipy.spatial.transform import Rotation as spRotation

# Create small numpy arrays with distinct dimensions
# global_orient: rotation vector, shape (batch, 3)
global_orient = np.array([
    [0.1, 0.2, 0.3],
    [0.05, 0.15, 0.25]
], dtype=np.float32)

# transl: translation, shape (batch, 3)
transl = np.array([
    [1.0, 2.0, 3.0],
    [1.5, 2.5, 3.5]
], dtype=np.float32)

# global_orient_offset: rotation vector offset, shape (3,)
global_orient_offset = np.array([0.05, 0.1, 0.15], dtype=np.float32)

# transl_offset: translation offset, shape (3,)
transl_offset = np.array([0.5, 0.6, 0.7], dtype=np.float32)

# root_location_t0: root location at time 0, shape (3,)
root_location_t0 = np.array([1.0, 2.0, 3.0], dtype=np.float32)

# pelvis_location_t0: pelvis location at time 0, shape (3,)
pelvis_location_t0 = np.array([1.1, 2.1, 3.1], dtype=np.float32)

ARGS = {
    "global_orient": global_orient,
    "transl": transl,
    "global_orient_offset": global_orient_offset,
    "transl_offset": transl_offset,
    "root_location_t0": root_location_t0,
    "pelvis_location_t0": pelvis_location_t0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, 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
get_humandata Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
openxrlab/xrfeitoria/xrfeitoria/utils/anim/motion.py
code served (permissive licence) · get_code("109afedda1495e7f")
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 dict. 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 numpy as np
from scipy.spatial.transform import Rotation as spRotation

# Create sample SMPL-X data
n_frames = 2
n_body_pose_dims = 63  # SMPL body pose (21 joints * 3)

smpl_x_data = {
    'global_orient': np.random.randn(n_frames, 3).astype(np.float32),
    'transl': np.random.randn(n_frames, 3).astype(np.float32),
    'body_pose': np.random.randn(n_frames, n_body_pose_dims).astype(np.float32),
}

# Create betas (shape parameters: 10-dim for SMPL)
betas = np.random.randn(10).astype(np.float32)

# Create optional parameters
meta = {'source': 'test_data', 'sequence_id': 1}
global_orient_offset = np.array([0.1, 0.0, 0.0], dtype=np.float32)
transl_offset = np.array([0.5, 0.0, 0.0], dtype=np.float32)
root_location_t0 = np.array([0.0, 0.0, 0.0], dtype=np.float32)
pelvis_location_t0 = np.array([0.0, 1.0, 0.0], dtype=np.float32)

ARGS = {
    'smpl_x_data': smpl_x_data,
    'smpl_x_type': 'smpl',
    'betas': betas,
    'meta': meta,
    'global_orient_offset': global_orient_offset,
    'transl_offset': transl_offset,
    'root_location_t0': root_location_t0,
    'pelvis_location_t0': pelvis_location_t0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
SMPLXMotion Not yet run
unverified (harvested, no recorded run)
openxrlab/xrfeitoria/xrfeitoria/utils/anim/motion.py
code served (permissive licence) · get_code("dd42229e2afc1c4b")
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, 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 6 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

Estimating human and camera trajectories with accurate scale in the world coordinate system from a monocular video is a highly desirable yet challenging and ill-posed problem. In this study, we aim to recover expressive parametric human models (i.e., SMPL-X) and corresponding camera poses jointly, by leveraging the synergy between three critical players: the world, the human, and the camera. Our approach is founded on two key observations. Firstly, camera-frame SMPL-X estimation methods readily recover absolute human depth. Secondly, human motions inherently provide absolute spatial cues. By integrating these insights, we introduce a novel framework, referred to as WHAC, to facilitate world-grounded expressive human pose and shape estimation (EHPS) alongside camera pose estimation, without relying on traditional optimization techniques. Additionally, we present a new synthetic dataset, WHAC-A-Mole, which includes accurately annotated humans and cameras, and features diverse interactive human motions as well as realistic camera trajectories. Extensive experiments on both standard and newly established benchmarks highlight the superiority and efficacy of our framework. The code and dataset are available on the homepage 1 .

For agents

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

get_harvested_code_for_paper("2403.12959")
get_code_for_paper("2403.12959")
have("2403.12959")

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

curl https://syntology.ai/api/ran/2403.12959.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.12959.svg)](https://syntology.ai/paper/2403.12959)

Connect an agent — have() is free.