SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.02467 · CVPR · 2021

Body Meshes as Points

Jiashi Feng, Jianfeng Zhang, Dongdong Yu, Jun Liew, Xuecheng Nie

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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 1 has no contract verdict; 5 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/2105.02467.json · badge: /api/ran/2105.02467.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
jfzhang95/BMP canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
batch_adv_disc_l2_loss Ran
ran; our contract draft was wrong, not the code
jfzhang95/BMP/mmdetection/mmdet/models/losses/bmp_loss.py
code served (permissive licence) · get_code("c8bb80a7e1410dce")
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 torch

torch.manual_seed(0)

# Create small tensors for real and fake discriminator values
# real_disc_value: shape (2, 4) - batch size 2, 4-dim output
# fake_disc_value: shape (3, 4) - batch size 3, 4-dim output (different batch size to show distinction)
real_disc_value = torch.randn(2, 4)
fake_disc_value = torch.randn(3, 4)

ARGS = {
    "real_disc_value": real_disc_value,
    "fake_disc_value": fake_disc_value
}
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, 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
batch_encoder_disc_l2_loss Ran
ran; our contract draft was wrong, not the code
jfzhang95/BMP/mmdetection/mmdet/models/losses/bmp_loss.py
code served (permissive licence) · get_code("cfe9fa681dd0306f")
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 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)

# Construct a small disc_value tensor
# The function accesses disc_value.shape[0] and performs operations on it
# Shape: (batch_size, ...) where batch_size will be k
disc_value = torch.randn(2, 4)

ARGS = {
    "disc_value": disc_value
}
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 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
jfzhang95/BMP/mmcv/mmcv/cnn/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from whai362/PytorchInsight, is pointer only (licence: NONE) · get_code("77f89e05c55c985d")
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 whai362/PytorchInsight, 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.

make_res_layer Ran
ran on a synthesized input
jfzhang95/BMP/mmcv/mmcv/cnn/resnet.py
code served (permissive licence) · get_code("d0257b12c85879e1")
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 Sequential. 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

torch.manual_seed(0)

class BasicBlock(nn.Module):
    expansion = 1
    
    def __init__(self, inplanes, planes, stride=1, dilation=1, downsample=None, style='pytorch', with_cp=False):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if self.downsample is not None:
            identity = self.downsample(x)
        out += identity
        out = self.relu(out)
        return out

ARGS = {
    'block': BasicBlock,
    'inplanes': 64,
    'planes': 64,
    'blocks': 3,
    'stride': 1,
    'dilation': 1,
    'style': 'pytorch',
    'with_cp': False
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
nms_oks Ran
ran; our contract draft was wrong, not the code
jfzhang95/BMP/mmdetection/mmdet/models/smpl_heads/bmp_head.py
code served (permissive licence) · get_code("71fa504e10fb7b83")
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 numpy as np

torch.manual_seed(0)

# Build minimal valid arguments for nms_oks function
# kp_predictions: BxKx2 (batch of keypoint predictions)
# rois: Bx5 (batch of ROIs with last column being scores)
# thresh: float (OKS threshold)

batch_size = 2
num_keypoints = 24
num_rois = 2

# kp_predictions: BxKx2 - keypoint predictions for each ROI
kp_predictions = torch.randn(num_rois, num_keypoints, 2, dtype=torch.float32)

# rois: Bx5 - each ROI has [x1, y1, x2, y2, score]
# x1, y1, x2, y2 define bounding box, last dim is score
rois = torch.tensor([
    [10.0, 20.0, 100.0, 150.0, 0.9],
    [15.0, 25.0, 110.0, 160.0, 0.7]
], dtype=torch.float32)

# thresh: float - OKS threshold for NMS
thresh = 0.5

ARGS = {
    "kp_predictions": kp_predictions,
    "rois": rois,
    "thresh": thresh
}
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 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
points_nms Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jfzhang95/BMP/mmdetection/mmdet/models/smpl_heads/bmp_head.py
code served (permissive licence) · get_code("52f11102df1da218")
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 4, dtype family float, shape (2, 3, 4, 5) 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 torch.nn as nn

torch.manual_seed(0)

# Create a small heat map tensor
# Shape: (batch=2, channels=3, height=4, width=5)
heat = torch.randn(2, 3, 4, 5)

ARGS = {
    "heat": heat,
    "kernel": 2
}
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 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 3, 4, 5) 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_oks Not yet run
unverified (harvested, no recorded run)
jfzhang95/BMP/mmdetection/mmdet/models/smpl_heads/bmp_head.py
code served (permissive licence) · get_code("4efc5055d45add3f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 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
conv3x3 18 other papers
8 dated earlier, 10 later
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1901.04780 (2019-01)
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
1905.09646 (2019-05)
Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks
and 15 more not named here
batch_adv_disc_l2_loss 1 other paper
1 later
2109.02303 (2021-09)
Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation
batch_encoder_disc_l2_loss 1 other paper
1 later
2109.02303 (2021-09)
Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation
make_res_layer 1 other paper
1 later
2107.04941 (2021-07)
Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We consider the challenging multi-person 3D body mesh estimation task in this work. Existing methods are mostly two-stage based-one stage for person localization and the other stage for individual body mesh estimation, leading to redundant pipelines with high computation cost and degraded performance for complex scenes (e.g. troduces a novel keypoint-aware augmentation to enhance model robustness to occluded person instances. Comprehensive experiments on benchmarks Panoptic, MuPoTS-3D and 3DPW clearly demonstrate the state-of-the-art efficiency of BMP for multi-person body mesh estimation, together with outstanding accuracy. Code can be found at: https://github.com/jfzhang95/BMP.

For agents

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

get_harvested_code_for_paper("2105.02467")
get_code_for_paper("2105.02467")
have("2105.02467")

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

curl https://syntology.ai/api/ran/2105.02467.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.02467.svg)](https://syntology.ai/paper/2105.02467)

Connect an agent — have() is free.