SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.02548 · ICLR · 2025

Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation

Salman Khan, Angela Dai, Rao Anwer, Shahbaz Fahad, Khan, Mohamed El, Amine Boudjoghra, Jean Lahoud, Hisham Cholakkal

arXiv · PDF · Open in the Atlas

Code that ran

4 of 11 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, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 7 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/2406.02548.json · badge: /api/ran/2406.02548.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
aminebdj/openyolo3d canonical (classifier label)
classifier basis: census
4 ran · 4 no recorded run
aminebdj/OpenYOLO3D canonical (classifier label)
classifier basis: classifier_2025
0 ran · 3 no recorded run
FunctionStatusWhere it lives
get_image_resolution Ran
ran, honoured the contract we drafted
aminebdj/openyolo3d/utils/utils_2d.py
pointer only (licence: NONE) · get_code("a2c0b7667d1bb3f5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminebdj/openyolo3d 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.

load_yaml Ran
ran; our contract draft was wrong, not the code
aminebdj/openyolo3d/run_evaluation.py
pointer only (licence: NONE) · get_code("9fd328d58844f055")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminebdj/openyolo3d 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_label_mapping Ran
ran; our contract draft was wrong, not the code
aminebdj/openyolo3d/evaluate/scannet200/util.py
pointer only (licence: NONE) · get_code("d77ef48746ee7ff1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminebdj/openyolo3d 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.

represents_int Ran
ran, violated the contract we drafted
aminebdj/openyolo3d/evaluate/scannet200/util.py
pointer only (licence: NONE) · get_code("945af43d6054ff01")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminebdj/openyolo3d 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_averages Not yet run
unverified (harvested, no recorded run)
aminebdj/OpenYOLO3D/evaluate/replica/eval_semantic_instance.py
pointer only (licence: NONE) · get_code("e2d190ab0e997db4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminebdj/OpenYOLO3D 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.

evaluate_matches Not yet run
unverified (harvested, no recorded run)
aminebdj/OpenYOLO3D/evaluate/replica/eval_semantic_instance.py
pointer only (licence: NONE) · get_code("d9c5945898e9b307")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminebdj/OpenYOLO3D 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.

load_ids Not yet run
unverified (harvested, no recorded run)
aminebdj/openyolo3d/evaluate/scannet200/util_3d.py
pointer only (licence: NONE) · get_code("8860634b31a744dc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminebdj/openyolo3d 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.

make_pred_info Not yet run
unverified (harvested, no recorded run)
aminebdj/OpenYOLO3D/evaluate/replica/eval_semantic_instance.py
pointer only (licence: NONE) · get_code("2f0819a20a8970d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminebdj/OpenYOLO3D 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.

read_mesh_vertices Not yet run
unverified (harvested, no recorded run)
aminebdj/openyolo3d/evaluate/scannet200/util_3d.py
pointer only (licence: NONE) · get_code("e47cf090e9fda5a8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminebdj/openyolo3d 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.

read_scene_types_mapping Not yet run
unverified (harvested, no recorded run)
aminebdj/openyolo3d/evaluate/scannet200/util.py
pointer only (licence: NONE) · get_code("42c8e07d575c5757")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminebdj/openyolo3d 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.

transform_points Not yet run
unverified (harvested, no recorded run)
aminebdj/openyolo3d/evaluate/scannet200/util_3d.py
pointer only (licence: NONE) · get_code("be96878cd262fb03")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminebdj/openyolo3d 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
represents_int 7 other papers
6 dated earlier, 1 later
1906.01140 (2019-06)
Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
aaai_16558 (2021 (year only))
DocParser: Hierarchical Document Structure Parsing from Renderings
2306.03908 (2023-06)
SAM3D: Segment Anything in 3D Scenes
and 4 more not named here
load_ids 5 other papers
5 dated earlier
2004.01658 (2020-04)
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
2203.09065 (2022-03)
STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
2203.16832 (2022-03)
Point Scene Understanding via Disentangled Instance Mesh Reconstruction
and 2 more not named here
read_mesh_vertices 5 other papers
5 dated earlier
2203.05238 (2022-03)
Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement
2203.09065 (2022-03)
STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
aaai_25335 (2023 (year only))
Superpoint Transformer for 3D Scene Instance Segmentation
and 2 more not named here
read_label_mapping 4 other papers
4 dated earlier
1906.01140 (2019-06)
Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
2306.03908 (2023-06)
SAM3D: Segment Anything in 3D Scenes
2311.17707 (2023-11)
SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation
and 1 more not named here
transform_points 3 other papers
3 dated earlier
2203.09065 (2022-03)
STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
aaai_25335 (2023 (year only))
Superpoint Transformer for 3D Scene Instance Segmentation
2303.00246 (2023-03)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution
compute_averages 2 other papers
2 dated earlier
2210.03105 (2022-10)
Mask3D: Mask Transformer for 3D Semantic Instance Segmentation
2309.00616 (2023-09)
OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation
evaluate_matches 2 other papers
2 dated earlier
2210.03105 (2022-10)
Mask3D: Mask Transformer for 3D Semantic Instance Segmentation
2309.00616 (2023-09)
OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation
read_scene_types_mapping 1 other paper
1 dated earlier
2306.03908 (2023-06)
SAM3D: Segment Anything in 3D Scenes

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

Recent works on open-vocabulary 3D instance segmentation show strong promise, but at the cost of slow inference speed and high computation requirements. This high computation cost is typically due to their heavy reliance on 3D clip features, which require computationally expensive 2D foundation models like Segment Anything (SAM) and CLIP for multi-view aggregation into 3D. As a consequence, this hampers their applicability in many real-world applications that require both fast and accurate predictions. To this end, we propose a fast yet accurate openvocabulary 3D instance segmentation approach, named Open-YOLO 3D, that effectively leverages only 2D object detection from multi-view RGB images for open-vocabulary 3D instance segmentation. We address this task by generating class-agnostic 3D masks for objects in the scene and associating them with text prompts. We observe that the projection of class-agnostic 3D point cloud instances already holds instance information; thus, using SAM might only result in redundancy that unnecessarily increases the inference time. We empirically find that a better performance of matching text prompts to 3D masks can be achieved in a faster fashion with a 2D object detector. We validate our Open-YOLO 3D on two benchmarks, ScanNet200 and Replica, under two scenarios: (i) with ground truth masks, where labels are required for given object proposals, and (ii) with class-agnostic 3D proposals generated from a 3D proposal network. Our Open-YOLO 3D achieves state-of-the-art performance on both datasets while obtaining up to ∼16× speedup compared to the best existing method in literature. On Scan-Net200 val. set, our Open-YOLO 3D achieves mean average precision (mAP) of 24.7% while operating at 22 seconds per scene. Code and model are available at github.com/aminebdj/OpenYOLO3D

For agents

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

get_harvested_code_for_paper("2406.02548")
get_code_for_paper("2406.02548")
have("2406.02548")

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

curl https://syntology.ai/api/ran/2406.02548.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.02548.svg)](https://syntology.ai/paper/2406.02548)

Connect an agent — have() is free.