SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.14048 · CVPR · 2022

Learning Deep Implicit Functions for 3D Shapes with Dynamic Code Clouds

Xin Wen, Yu-Shen Liu, Zhizhong Han, Tianyang Li, Hua Su

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 0 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/2203.14048.json · badge: /api/ran/2203.14048.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
lity20/DCCDIF community
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
CodeCloud Ran
ran on a synthesized input · constructed an object; no result was computed
lity20/DCCDIF/network.py
code served (permissive licence) · get_code("0890b5f6431fc5f6")
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, CodeCloud: 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 config dict with required keys
config = {
    'num_codes': 5,
    'code_dim': 4,
    'dist_scale': 2.0
}

# Define num_records
num_records = 3

# Create the ARGS dict
ARGS = {
    'config': config,
    'num_records': num_records
}
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 CodeCloud — 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 CodeCloud 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
IM_Decoder Ran
ran on a synthesized input · constructed an object; no result was computed
lity20/DCCDIF/network.py
code served (permissive licence) · get_code("909237c65ad4be71")
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, IM_Decoder: 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)

# IM_Decoder takes input_dim as a parameter
# Looking at the forward method, batch_input is concatenated with layer outputs
# The input_dim should match the feature dimension of batch_input
input_dim = 64

ARGS = {
    'input_dim': input_dim,
}
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 IM_Decoder — 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 IM_Decoder 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
Network Ran
ran on a synthesized input · constructed an object; no result was computed
lity20/DCCDIF/network.py
code served (permissive licence) · get_code("d11c5720cf340276")
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, Network: 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)

# Configuration dict with all required fields
config = {
    'code_cloud': {
        'num_codes': 4,
        'code_dim': 8,
        'dist_scale': 2.0,
    },
    'code_regularization_lambda': 0.1,
    'code_position_lambda': 0.05,
}

# Number of records in the database
num_records = 3

ARGS = {
    'config': config,
    'num_records': num_records,
}
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 Network — 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 Network 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 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.

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

Deep Implicit Function (DIF) has gained popularity as an efficient 3D shape representation. To capture geometry details, current methods usually learn DIF using local latent codes, which discretize the space into a regular 3D grid (or octree) and store local codes in grid points (or octree nodes). Given a query point, the local feature is computed by interpolating its neighboring local codes with their positions. However, the local codes are constrained at discrete and regular positions like grid points, which makes the code positions difficult to be optimized and limits their representation ability. To solve this problem, we propose to learn DIF with Dynamic Code Cloud, named DCC-DIF. Our method explicitly associates local codes with learnable position vectors, and the position vectors are continuous and can be dynamically optimized, which improves the representation ability. In addition, we propose a novel code position loss to optimize the code positions, which heuristically guides more local codes to be distributed around complex geometric details. In contrast to previous methods, our DCC-DIF represents 3D shapes more efficiently with a small amount of local codes, and improves the reconstruction quality. Experiments demonstrate that DCC-DIF achieves better performance over previous methods. Code and data are available at https://github.com/lity20/DCCDIF.

For agents

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

get_harvested_code_for_paper("2203.14048")
get_code_for_paper("2203.14048")
have("2203.14048")

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

curl https://syntology.ai/api/ran/2203.14048.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.14048.svg)](https://syntology.ai/paper/2203.14048)

Connect an agent — have() is free.