SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.09502 · CVPR · 2023

Sampling is Matter: Point-guided 3D Human Mesh Reconstruction

Jeonghwan Kim, Hyunwoo Park, Gi-Mun Um, Mi-Gyeong Gwon, Wonjun Kim, Hyukmin Kwon

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 1 failure of our instrument; 3 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/2304.09502.json · badge: /api/ran/2304.09502.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
DCVL-3D/PointHMR_release marked official in Papers with Code
Papers with Code archive
5 ran · 3 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input
DCVL-3D/PointHMR_release/src/modeling/model/network.py
code served (permissive licence) · get_code("51f7fa0f3860d4e6")
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 Tensor, ndim 4, 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
import torch.nn as nn

BN_MOMENTUM = 0.1

def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False)

class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = 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:
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out

downsample_module = nn.Sequential(
    nn.Conv2d(3, 8, kernel_size=1, stride=2, bias=False),
    nn.BatchNorm2d(8, momentum=BN_MOMENTUM)
)

INIT_ARGS = {
    'inplanes': 3,
    'planes': 8,
    'stride': 2,
    'downsample': downsample_module
}

ARGS = {
    'x': torch.randn(2, 3, 16, 16)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 — 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)
Bottleneck Ran
ran on a synthesized input
DCVL-3D/PointHMR_release/src/modeling/model/network.py
code served (permissive licence) · get_code("b1366029d2881025")
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 Tensor, ndim 4, 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
import torch.nn as nn

BN_MOMENTUM = 0.1

class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None, BN=nn.BatchNorm2d):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = BN(planes, momentum=BN_MOMENTUM)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.conv3 = nn.Conv2d(planes, planes * self.expansion, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * self.expansion, momentum=BN_MOMENTUM)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)
        out = self.conv3(out)
        out = self.bn3(out)
        if self.downsample is not None:
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out

downsample_module = nn.Sequential(
    nn.Conv2d(8, 16, kernel_size=1, stride=1, bias=False),
    nn.BatchNorm2d(16, momentum=BN_MOMENTUM)
)

INIT_ARGS = {
    'inplanes': 8,
    'planes': 4,
    'stride': 1,
    'downsample': downsample_module,
    'BN': nn.BatchNorm2d
}

ARGS = {
    'x': torch.randn(2, 8, 7, 7)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 — 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)
HighResolutionModule Ran
ran on a synthesized input · constructed an object; no result was computed
DCVL-3D/PointHMR_release/src/modeling/model/network.py
code served (permissive licence) · get_code("fba177fc8e06573b")
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, HighResolutionModule: 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Define a minimal block class that the module uses
class BasicBlock(nn.Module):
    expansion = 1
    
    def __init__(self, inplanes, planes, stride=1, downsample=None):
        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

# Build arguments for HighResolutionModule
num_branches = 2
blocks = BasicBlock
num_blocks = [2, 2]  # 2 blocks per branch
num_inchannels = [64, 128]  # input channels for each branch
num_channels = [64, 128]  # output channels for each branch
fuse_method = 'sum'
multi_scale_output = True

ARGS = {
    'num_branches': num_branches,
    'blocks': blocks,
    'num_blocks': num_blocks,
    'num_inchannels': num_inchannels,
    'num_channels': num_channels,
    'fuse_method': fuse_method,
    'multi_scale_output': multi_scale_output
}
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 HighResolutionModule — 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 HighResolutionModule 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
build_position_encoding Ran
ran; our contract draft was wrong, not the code
DCVL-3D/PointHMR_release/src/modeling/model/network.py
code served (permissive licence) · get_code("c62bd3602bcf3ba2")
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 PositionEmbeddingSine. 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
from torch import nn
import math

torch.manual_seed(0)

ARGS = {
    "hidden_dim": 128
}
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 PositionEmbeddingSine — a PositionEmbeddingSine output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PositionEmbeddingSine 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
copy_state_dict Ran
ran, honoured the contract we drafted
DCVL-3D/PointHMR_release/src/modeling/model/network.py
code served (permissive licence) · get_code("da69a7ce867e0cd6")
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 list, 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
import torch.nn as nn
import logging

torch.manual_seed(0)

# Configure logging to avoid cluttering output
logging.basicConfig(level=logging.INFO)

# Create a simple model to extract state dicts from
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = nn.Linear(4, 3)
        self.layer2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        return x

# Create current model and its state dict
current_model = SimpleModel()
cur_state_dict = current_model.state_dict()

# Create pre-trained model and its state dict (with module. prefix)
pretrained_model = SimpleModel()
pre_state_dict_raw = pretrained_model.state_dict()

# Add 'module.' prefix to simulate DataParallel saved model
pre_state_dict = {}
for k, v in pre_state_dict_raw.items():
    pre_state_dict['module.' + k] = v.clone()

# Make tensors require grad so requires_grad assignment works
for key in cur_state_dict:
    cur_state_dict[key].requires_grad = True

ARGS = {
    'cur_state_dict': cur_state_dict,
    'pre_state_dict': pre_state_dict,
    'prefix': 'module.',
    'drop_prefix': '',
    'fix_loaded': 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 list, ndim 1, dtype family float — a list 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
HigherResolutionNet Not yet run
unverified (harvested, no recorded run)
DCVL-3D/PointHMR_release/src/modeling/model/network.py
code served (permissive licence) · get_code("aa657ca635438a4b")
How it ran

no invocation recorded.

MeshRegressor Not yet run
unverified (harvested, no recorded run)
DCVL-3D/PointHMR_release/src/modeling/model/network.py
code served (permissive licence) · get_code("0a5fd5749f28c2ad")
How it ran

no invocation recorded.

PointHMR Not yet run
unverified (harvested, no recorded run)
DCVL-3D/PointHMR_release/src/modeling/model/network.py
code served (permissive licence) · get_code("d7086278e0c85c61")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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, 2 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.

FunctionAlso present inEarliest-datedOthers named
BasicBlock
brick of this paper's assembly: helper
4 other papers
3 dated earlier, 1 later · 3 only as an assembly brick
2107.02156 (2021-07)
Do Different Tracking Tasks Require Different Appearance Models?
2203.11018 (2022-03)
Stereo Neural Vernier Caliper
2205.01271 (2022-05)
Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation
and 1 more not named here
build_position_encoding
brick of this paper's assembly: helper
1 other paper
1 later
2403.01813 (2024-03)
A Simple Baseline for Efficient Hand Mesh Reconstruction

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

This paper presents a simple yet powerful method for 3D human mesh reconstruction from a single RGB image. Most recently, the non-local interactions of the whole mesh vertices have been effectively estimated in the transformer while the relationship between body parts also has begun to be handled via the graph model. Even though those approaches have shown the remarkable progress in 3D human mesh reconstruction, it is still difficult to directly infer the relationship between features, which are encoded from the 2D input image, and 3D coordinates of each vertex. To resolve this problem, we propose to design a simple feature sampling scheme. The key idea is to sample features in the embedded space by following the guide of points, which are estimated as projection results of 3D mesh vertices (i.e., ground truth). This helps the model to concentrate more on vertex-relevant features in the 2D space, thus leading to the reconstruction of the natural human pose. Furthermore, we apply progressive attention masking to precisely estimate local interactions between vertices even under severe occlusions. Experimental results on benchmark datasets show that the proposed method efficiently improves the performance of 3D human mesh reconstruction.

For agents

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

get_harvested_code_for_paper("2304.09502")
get_code_for_paper("2304.09502")
have("2304.09502")

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

curl https://syntology.ai/api/ran/2304.09502.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.09502.svg)](https://syntology.ai/paper/2304.09502)

Connect an agent — have() is free.