SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.04714 · NeurIPS · 2025

Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction

Kunho Heo, Gihyun Kim, Suyeon Kim, Myeongah Cho

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2510.04714.json · badge: /api/ran/2510.04714.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
VisualScienceLab-KHU/OCRL-3DSSG-Codes canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
FunctionStatusWhere it lives
Parser Ran
ran; our contract draft was wrong, not the code
VisualScienceLab-KHU/OCRL-3DSSG-Codes/data_processing/gen_data_gt.py
pointer only (licence: NONE) · get_code("1dd44bbe572b95d9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualScienceLab-KHU/OCRL-3DSSG-Codes 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.

collate_fn_obj Ran
ran; our contract draft was wrong, not the code
VisualScienceLab-KHU/OCRL-3DSSG-Codes/src/dataset/DataLoader.py
pointer only (licence: NONE) · get_code("13c75d97c43c9aca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualScienceLab-KHU/OCRL-3DSSG-Codes 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.

collate_fn_obj_new Ran
ran; our contract draft was wrong, not the code
VisualScienceLab-KHU/OCRL-3DSSG-Codes/src/dataset/DataLoader.py
pointer only (licence: NONE) · get_code("fb8d659261381bf7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualScienceLab-KHU/OCRL-3DSSG-Codes 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.

collate_fn_rel Ran
ran; our contract draft was wrong, not the code
VisualScienceLab-KHU/OCRL-3DSSG-Codes/src/dataset/DataLoader.py
pointer only (licence: NONE) · get_code("cbd67f45aee69397")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualScienceLab-KHU/OCRL-3DSSG-Codes 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.

compute Ran
ran, honoured the contract we drafted
VisualScienceLab-KHU/OCRL-3DSSG-Codes/data_processing/compute_weight_occurrences.py
pointer only (licence: NONE) · get_code("72485f52d0f05d21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualScienceLab-KHU/OCRL-3DSSG-Codes 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.

compute_weights Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
VisualScienceLab-KHU/OCRL-3DSSG-Codes/data_processing/compute_weight_occurrences.py
pointer only (licence: NONE) · get_code("81efbab1f77a0b49")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualScienceLab-KHU/OCRL-3DSSG-Codes 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.

gen_splits Ran
ran; our contract draft was wrong, not the code
VisualScienceLab-KHU/OCRL-3DSSG-Codes/data_processing/generate_train_valid_test_splits.py
pointer only (licence: NONE) · get_code("18f66e0f05a51f62")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualScienceLab-KHU/OCRL-3DSSG-Codes 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.

gen_splits_scannet Ran
ran; our contract draft was wrong, not the code
VisualScienceLab-KHU/OCRL-3DSSG-Codes/data_processing/generate_train_valid_test_splits.py
pointer only (licence: NONE) · get_code("f91e25982421a5ae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualScienceLab-KHU/OCRL-3DSSG-Codes 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.

read_txt_to_list Ran
ran; our contract draft was wrong, not the code
VisualScienceLab-KHU/OCRL-3DSSG-Codes/data_processing/generate_train_valid_test_splits.py
pointer only (licence: NONE) · get_code("66a478b6bf5949d5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualScienceLab-KHU/OCRL-3DSSG-Codes 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.

build_model Not yet run
unverified (harvested, no recorded run)
VisualScienceLab-KHU/OCRL-3DSSG-Codes/clip_adapter/clip/model.py
pointer only (licence: NONE) · get_code("0b01acb5bc3f8968")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualScienceLab-KHU/OCRL-3DSSG-Codes 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. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 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.

FunctionAlso present inEarliest-datedOthers named
build_model 1 other paper
1 dated earlier
2411.06921 (2024-11)
UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models

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

3D Semantic Scene Graph Prediction aims to detect objects and their semantic relationships in 3D scenes, and has emerged as a crucial technology for robotics and AR/VR applications. While previous research has addressed dataset limitations and explored various approaches including Open-Vocabulary settings, they frequently fail to optimize the representational capacity of object and relationship features, showing excessive reliance on Graph Neural Networks despite insufficient discriminative capability. In this work, we demonstrate through extensive analysis that the quality of object features plays a critical role in determining overall scene graph accuracy. To address this challenge, we design a highly discriminative object feature encoder and employ a contrastive pretraining strategy that decouples object representation learning from the scene graph prediction. This design not only enhances object classification accuracy but also yields direct improvements in relationship prediction. Notably, when plugging in our pretrained encoder into existing frameworks, we observe substantial performance improvements across all evaluation metrics. Additionally, whereas existing approaches have not fully exploited the integration of relationship information, we effectively combine both geometric and semantic features to achieve superior relationship prediction. Comprehensive experiments on the 3DSSG dataset demonstrate that our approach significantly outperforms previous state-of-the-art methods. Our code is publicly available at https://github.com/VisualScienceLab-KHU/OCRL-3DSSG-Codes.

For agents

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

get_harvested_code_for_paper("2510.04714")
get_code_for_paper("2510.04714")
have("2510.04714")

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

curl https://syntology.ai/api/ran/2510.04714.json

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

[![Syntology run record](https://syntology.ai/api/ran/2510.04714.svg)](https://syntology.ai/paper/2510.04714)

Connect an agent — have() is free.