SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.02788 · 2020

Self-Supervised Scene De-occlusion

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 1 failure of our instrument; 1 no recorded run), measured 2026-11-21; 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/2004.02788.json · badge: /api/ran/2004.02788.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
ducminhkhoi/Amodal-Instance-Seg-ASBU community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
xiaohangzhan/deocclusion community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
FunctionStatusWhere it lives
gram_matrix Ran
ran on a synthesized input
ducminhkhoi/Amodal-Instance-Seg-ASBU/models/losses.py
code served (permissive licence) · get_code("1715f300a6a58899")
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 3, dtype family float, shape (2, 4, 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 torch

torch.manual_seed(0)

# Create a small feature tensor with shape (batch=2, channels=4, height=3, width=5)
# Using distinct sizes: batch=2, ch=4, h=3, w=5 to make dimensions unambiguous
feat = torch.randn(2, 4, 3, 5)

ARGS = {
    'feat': feat
}
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 3, dtype family float, shape (2, 4, 4) — shape (2, 4, 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
net_forward Ran
ran on a synthesized input
ducminhkhoi/Amodal-Instance-Seg-ASBU/inference.py
code served (permissive licence) · get_code("9950d3dd6df462d7")
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 int, shape (32, 32) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import numpy as np

torch.manual_seed(0)

# Build a minimal model that satisfies the function's usage
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv = nn.Conv2d(2, 2, kernel_size=3, padding=1)
    
    def forward(self, inmodal_patch, image=None):
        # Handle both single input and dual input cases
        output = self.conv(inmodal_patch)
        return output

class ModelWrapper:
    def __init__(self):
        self.model = MinimalModel()

# Build a minimal args object with all required attributes
class ArgsConfig:
    def __init__(self):
        self.model = {
            'use_std': False,
            'loss_mode': 'gaussian'
        }
        self.data = {
            'dataset': 'KINS',
            'use_default': False
        }
        # img_transform: converts numpy array to tensor
        self.img_transform = lambda x: torch.from_numpy(x).permute(2, 0, 1).float()

# Create instances
model_wrapper = ModelWrapper()
args_config = ArgsConfig()

# Create test data
image = np.random.rand(4, 3, 32, 32).astype(np.float32)  # HxWxC format expected
inmodal_patch = np.random.rand(32, 32).astype(np.float32)
eraser = np.random.rand(32, 32).astype(np.float32)

ARGS = {
    'model': model_wrapper,
    'image': image,
    'inmodal_patch': inmodal_patch,
    'eraser': eraser,
    'use_rgb': False,
    'th': 0.5,
    'args': args_config,
    'debug': False
}
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 ndarray, ndim 2, dtype family int, shape (32, 32) — shape (32, 32) 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
total_variation_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ducminhkhoi/Amodal-Instance-Seg-ASBU/models/losses.py
code served (permissive licence) · get_code("dedfa1b69056bdc7")
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)

# The function expects a 4D tensor (batch, channels, height, width)
# It computes total variation loss by comparing adjacent pixels
# Using small but distinct dimensions: batch=2, channels=3, height=4, width=5
image = torch.randn(2, 3, 4, 5)

ARGS = {
    "image": image
}
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
net_forward Not yet run
unverified (harvested, no recorded run)
xiaohangzhan/deocclusion/inference.py
code served (permissive licence) · get_code("157c70d96297d685")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 2 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
gram_matrix 6 other papers
2 dated earlier, 4 later
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.07723 (2018-04)
Image Inpainting for Irregular Holes Using Partial Convolutions
2010.09750 (2020-10)
Investigating and Simplifying Masking-based Saliency Methods for Model Interpretability
and 3 more not named here
total_variation_loss 5 other papers
2 dated earlier, 3 later
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.07723 (2018-04)
Image Inpainting for Irregular Holes Using Partial Convolutions
2010.09750 (2020-10)
Investigating and Simplifying Masking-based Saliency Methods for Model Interpretability
and 2 more not named here

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

Natural scene understanding is a challenging task, particularly when encountering images of multiple objects that are partially occluded. This obstacle is given rise by varying object ordering and positioning. Existing scene understanding paradigms are able to parse only the visible parts, resulting in incomplete and unstructured scene interpretation. In this paper, we investigate the problem of scene de-occlusion, which aims to recover the underlying occlusion ordering and complete the invisible parts of occluded objects. We make the first attempt to address the problem through a novel and unified framework that recovers hidden scene structures without ordering and amodal annotations as supervisions. This is achieved via Partial Completion Network (PCNet)-mask (M) and -content (C), that learn to recover fractions of object masks and contents, respectively, in a self-supervised manner. Based on PCNet-M and PCNet-C, we devise a novel inference scheme to accomplish scene de-occlusion, via progressive ordering recovery, amodal completion and content completion. Extensive experiments on real-world scenes demonstrate the superior performance of our approach to other alternatives. Remarkably, our approach that is trained in a self-supervised manner achieves comparable results to fully-supervised methods. The proposed scene de-occlusion framework benefits many applications, including high-quality and controllable image manipulation and scene recomposition (see Fig. 1), as well as the conversion of existing modal mask annotations to amodal mask annotations.

For agents

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

get_harvested_code_for_paper("2004.02788")
get_code_for_paper("2004.02788")
have("2004.02788")

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

curl https://syntology.ai/api/ran/2004.02788.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.02788.svg)](https://syntology.ai/paper/2004.02788)

Connect an agent — have() is free.