SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.05770 · 2020

Weakly Supervised Generative Network for Multiple 3D Human Pose Hypotheses

arXiv · PDF · Open in the Atlas

Code that ran

2 of 11 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 2 have no contract verdict; 0 failures of our instrument; 9 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/2008.05770.json · badge: /api/ran/2008.05770.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
chaneyddtt/weakly-supervised-3d-pose-generator canonical (classifier label)
classifier basis: census
2 ran · 9 no recorded run
FunctionStatusWhere it lives
err_3dpe Ran
ran on a synthesized input
chaneyddtt/weakly-supervised-3d-pose-generator/eval_functions.py
code served (permissive licence) · get_code("9d3cc432f01a5229")
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 float64, 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 numpy as np

# Create small sample 3D point clouds
# p_ref: reference points (3 x num_points)
# p: predicted points (3 x num_points)

np.random.seed(0)

# Create 3 points with 3 coordinates each
num_points = 4
p_ref = np.random.randn(3, num_points).astype(np.float64)
p = np.random.randn(3, num_points).astype(np.float64)

ARGS = {
    'p_ref': p_ref,
    'p': p,
    'procruste': 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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
weightedsample Ran
ran on a synthesized input
chaneyddtt/weakly-supervised-3d-pose-generator/ops.py
code served (permissive licence) · get_code("545bd5e99804c3ee")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Create small sample tensors
# The function uses tf.shape(realsample)[0] to get batch size
# and performs element-wise operations between realsample and fakesample
# so they need compatible shapes

batch_size = 2
feature_dim = 4

realsample = tf.constant(np.random.randn(batch_size, feature_dim).astype(np.float32))
fakesample = tf.constant(np.random.randn(batch_size, feature_dim).astype(np.float32))

ARGS = {
    'realsample': realsample,
    'fakesample': fakesample
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
bias_variable Not yet run
unverified (harvested, no recorded run)
chaneyddtt/weakly-supervised-3d-pose-generator/layers.py
code served (permissive licence) · get_code("9fdd8216a2990a2b")
How it ran

no invocation recorded.

fc_layer_linear Not yet run
unverified (harvested, no recorded run)
chaneyddtt/weakly-supervised-3d-pose-generator/layers.py
code served (permissive licence) · get_code("504c9c2b80f5cd48")
How it ran

no invocation recorded.

gp_loss Not yet run
unverified (harvested, no recorded run)
chaneyddtt/weakly-supervised-3d-pose-generator/mmd.py
code served (permissive licence) · get_code("9393f0343b979f8b")
How it ran

no invocation recorded.

mmd2 Not yet run
unverified (harvested, no recorded run)
chaneyddtt/weakly-supervised-3d-pose-generator/mmd.py
code served (permissive licence) · get_code("bf5921658e55ade2")
How it ran

no invocation recorded.

procrustes Not yet run
unverified (harvested, no recorded run)
chaneyddtt/weakly-supervised-3d-pose-generator/eval_functions.py
code served (permissive licence) · get_code("629ba7666349f226")
How it ran

no invocation recorded.

safer_norm Not yet run
unverified (harvested, no recorded run)
chaneyddtt/weakly-supervised-3d-pose-generator/mmd.py
code served (permissive licence) · get_code("a672706a6b3e25ae")
How it ran

no invocation recorded.

weight_variable Not yet run
unverified (harvested, no recorded run)
chaneyddtt/weakly-supervised-3d-pose-generator/layers.py
code served (permissive licence) · get_code("43d3063aefdee74a")
How it ran

no invocation recorded.

weighted_pose_2d_loss Not yet run
unverified (harvested, no recorded run)
chaneyddtt/weakly-supervised-3d-pose-generator/ops.py
code served (permissive licence) · get_code("81e49b933db41b17")
How it ran

no invocation recorded.

weighted_pose_2d_loss_mj Not yet run
unverified (harvested, no recorded run)
chaneyddtt/weakly-supervised-3d-pose-generator/ops.py
code served (permissive licence) · get_code("44d4829fafb6dc9f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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
bias_variable 3 other papers
3 dated earlier
1607.07539 (2016-07)
Semantic Image Inpainting with Deep Generative Models
1809.00888 (2018-09)
MesoNet: a Compact Facial Video Forgery Detection Network
1906.04569 (2019-06)
DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networks
mmd2 1 other paper
1 later
2010.09546 (2020-10)
Model-based Policy Optimization with Unsupervised Model Adaptation

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

3D human pose estimation from a single image is an inverse problem due to the inherent ambiguity of the missing depth. Several previous works addressed the inverse problem by generating multiple hypotheses. However, these works are strongly supervised and require ground truth 2D-to-3D correspondences which can be difficult to obtain. In this paper, we propose a weakly supervised deep generative network to address the inverse problem and circumvent the need for ground truth 2D-to-3D correspondences. To this end, we design our network to model a proposal distribution which we use to approximate the unknown multi-modal target posterior distribution. We achieve the approximation by minimizing the KL divergence between the proposal and target distributions, and this leads to a 2D reprojection error and a prior loss term that can be weakly supervised. Furthermore, we determine the most probable solution as the conditional mode of the samples using the mean-shift algorithm. We evaluate our method on three benchmark datasets -- Human3.6M, MPII and MPI-INF-3DHP. Experimental results show that our approach is capable of generating multiple feasible hypotheses and achieves state-of-the-art results compared to existing weakly supervised approaches. Our source code is available at the project website.

For agents

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

get_harvested_code_for_paper("2008.05770")
get_code_for_paper("2008.05770")
have("2008.05770")

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

curl https://syntology.ai/api/ran/2008.05770.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.05770.svg)](https://syntology.ai/paper/2008.05770)

Connect an agent — have() is free.