SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.00858 · CVPR · 2021

Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction

Feng Liu, Xiaoming Liu, Luan Tran

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 1 failure 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/2104.00858.json · badge: /api/ran/2104.00858.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
liuf1990/Fully_3D_Object community
Papers with Code archive
5 ran · 4 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input
liuf1990/Fully_3D_Object/SVR/network.py
code served (permissive licence) · get_code("96614e7522098178")
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

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)

def gn_init(m, zero_init=False):
    assert isinstance(m, nn.GroupNorm)
    m.weight.data.fill_(0.0 if zero_init else 1.0)
    m.bias.data.zero_()

class BasicBlock(nn.Module):
    expansion: int = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.GroupNorm(32, planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.GroupNorm(32, planes)
        self.downsample = downsample
        self.stride = stride
        gn_init(self.bn1)
        gn_init(self.bn2)

    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

# Setup with downsample
downsample = nn.Sequential(
    nn.Conv2d(32, 64, kernel_size=1, stride=2, bias=False),
    nn.GroupNorm(32, 64)
)

INIT_ARGS = {
    'inplanes': 32,
    'planes': 64,
    'stride': 2,
    'downsample': downsample
}

ARGS = {
    'x': torch.randn(2, 32, 8, 8)
}
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)
ImageEncoder Ran
ran on a synthesized input
liuf1990/Fully_3D_Object/SVR/network.py
code served (permissive licence) · get_code("49dc1d2b33abd1ce")
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 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
from scipy import stats

INIT_ARGS = {
    'fc_dim': 3,
    'fa_dim': 4,
    'fs_dim': 5,
    'light_dim': 6,
    'cam_dim': 2
}

# Create a small input tensor: batch=2, channels=3, height=8, width=8
input_tensor = torch.randn(2, 3, 8, 8)

ARGS = {
    'x': input_tensor
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, scipy, 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
ResNet Ran
ran on a synthesized input · constructed an object; no result was computed
liuf1990/Fully_3D_Object/SVR/network.py
code served (permissive licence) · get_code("29081d93c385e531")
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, ResNet: 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
import math

torch.manual_seed(0)

# Define a minimal ResidualBlock that satisfies the block interface
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.GroupNorm(32, 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.GroupNorm(32, 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,
    "layers": [2, 2, 2, 2],
    "num_classes": 1000
}
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 ResNet — 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 ResNet 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
ShapeDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
liuf1990/Fully_3D_Object/SVR/network.py
code served (permissive licence) · get_code("13f462877138a0db")
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, ShapeDecoder: 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
import torch.nn.functional as F

torch.manual_seed(0)

class ShapeDecoder(nn.Module):

    def __init__(self, fc_dim=3, fs_dim=256, num_branch=12, point_dim=3):
        super(ShapeDecoder, self).__init__()
        self.f_dim = fc_dim + fs_dim + point_dim
        self.sd_fc1 = nn.Linear(self.f_dim, 3072)
        self.sd_fc2 = nn.Linear(3072, 384)
        self.sd_fc3 = nn.Linear(384, num_branch)
        nn.init.normal_(self.sd_fc1.weight, mean=0.0, std=0.02)
        nn.init.constant_(self.sd_fc1.bias, 0)
        nn.init.normal_(self.sd_fc2.weight, mean=0.0, std=0.02)
        nn.init.constant_(self.sd_fc2.bias, 0)
        nn.init.normal_(self.sd_fc3.weight, mean=0.0, std=0.02)
        nn.init.constant_(self.sd_fc3.bias, 0)

    def forward(self, fc, fs, points):
        num_points = points.shape[1]
        fc = fc.unsqueeze(1).repeat(1, num_points, 1)
        fs = fs.unsqueeze(1).repeat(1, num_points, 1)
        fconca = torch.cat([fc, points, fs], dim=-1)
        l1 = self.sd_fc1(fconca)
        l1 = F.leaky_relu(l1, negative_slope=0.02, inplace=True)
        l2 = self.sd_fc2(l1)
        l2 = F.leaky_relu(l2, negative_slope=0.02, inplace=True)
        l3 = self.sd_fc3(l2)
        l3 = torch.sigmoid(l3)
        l4 = F.max_pool1d(l3, l3.shape[-1])
        return (l3, l4)

# Create model instance
model = ShapeDecoder(fc_dim=3, fs_dim=256, num_branch=12, point_dim=3)

# Create input tensors
# fc: batch_size x fc_dim
fc = torch.randn(2, 3)

# fs: batch_size x fs_dim
fs = torch.randn(2, 256)

# points: batch_size x num_points x point_dim
points = torch.randn(2, 4, 3)

ARGS = {
    'fc_dim': 3,
    'fs_dim': 256,
    'num_branch': 12,
    'point_dim': 3
}
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 ShapeDecoder — 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 ShapeDecoder 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
resnet18 Ran
ran; our contract draft was wrong, not the code
liuf1990/Fully_3D_Object/SVR/network.py
code served (permissive licence) · get_code("fcc5cd481cb71ade")
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 ResNet. 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
import math

torch.manual_seed(0)

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)

def gn_init(m, zero_init=False):
    assert isinstance(m, nn.GroupNorm)
    m.weight.data.fill_(0.0 if zero_init else 1.0)
    m.bias.data.zero_()

def conv2d_init(m):
    assert isinstance(m, nn.Conv2d)
    n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
    m.weight.data.normal_(0, math.sqrt(2.0 / n))

class BasicBlock(nn.Module):
    expansion: int = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.GroupNorm(32, planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.GroupNorm(32, planes)
        self.downsample = downsample
        self.stride = stride
        gn_init(self.bn1)
        gn_init(self.bn2)

    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

class ResNet(nn.Module):

    def __init__(self, block, layers, num_classes=1000):
        self.inplanes = 64
        super(ResNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.GroupNorm(32, 64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, num_classes)
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                conv2d_init(m)
        gn_init(self.bn1)

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False), nn.GroupNorm(32, planes * block.expansion))
            m = downsample[1]
            assert isinstance(m, nn.GroupNorm)
            gn_init(m)
        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))
        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

def resnet18(**kwargs):
    model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
    return model

ARGS = {
    "num_classes": 1000
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
AlbedoDecoder Not yet run
unverified (harvested, no recorded run)
liuf1990/Fully_3D_Object/SVR/network.py
code served (permissive licence) · get_code("40a68922959f191f")
How it ran

no invocation recorded.

SingleViewRecon Not yet run
unverified (harvested, no recorded run)
liuf1990/Fully_3D_Object/SVR/network.py
code served (permissive licence) · get_code("3673c4feddc85208")
How it ran

no invocation recorded.

conv2d_init Not yet run
unverified (harvested, no recorded run)
liuf1990/Fully_3D_Object/SVR/network.py
code served (permissive licence) · get_code("805e0dc957782a49")
How it ran

no invocation recorded.

gn_init Not yet run
unverified (harvested, no recorded run)
liuf1990/Fully_3D_Object/SVR/network.py
code served (permissive licence) · get_code("3810ceff872a9f8b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 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.

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

Inferring 3D structure of a generic object from a 2D image is a long-standing objective of computer vision. Conventional approaches either learn completely from CADgenerated synthetic data, which have difficulty in inference from real images, or generate 2.5D depth image via intrinsic decomposition, which is limited compared to the full 3D reconstruction. One fundamental challenge lies in how to leverage numerous real 2D images without any 3D ground truth. To address this issue, we take an alternative approach with semi-supervised learning. That is, for a 2D image of a generic object, we decompose it into latent representations of category, shape, albedo, lighting and camera projection matrix, decode the representations to segmented 3D shape and albedo respectively, and fuse these components to render an image well approximating the input image. Using a category-adaptive 3D joint occupancy field (JOF), we show that the complete shape and albedo modeling enables us to leverage real 2D images in both modeling and model fitting. The effectiveness of our approach is demonstrated through superior 3D reconstruction from a single image, being either synthetic or real, and shape segmentation. Code is available at http://cvlab.cse.msu. edu/project-fully3dobject.html.

For agents

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

get_harvested_code_for_paper("2104.00858")
get_code_for_paper("2104.00858")
have("2104.00858")

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

curl https://syntology.ai/api/ran/2104.00858.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.00858.svg)](https://syntology.ai/paper/2104.00858)

Connect an agent — have() is free.