SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.15933 · AAAI · 2024

Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA

Yang Liu, Wentao Mo

arXiv · PDF · Open in the Atlas

Code that ran

12 of 13 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; 4 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 7 failures of our instrument; 1 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/2402.15933.json · badge: /api/ran/2402.15933.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
matthewdm0816/bridgeqa canonical (classifier label)
classifier basis: census
12 ran · 1 no recorded run
FunctionStatusWhere it lives
construct_bbox_corners Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
matthewdm0816/bridgeqa/lib/eval_helper.py
pointer only (licence: NOASSERTION) · get_code("c1a3575f07494487")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, matthewdm0816/bridgeqa (NOASSERTION). 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.

create_enet Ran
ran; our contract draft was wrong, not the code
matthewdm0816/bridgeqa/lib/enet.py
pointer only (licence: NOASSERTION) · get_code("d209e4ea51338ac8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, matthewdm0816/bridgeqa (NOASSERTION). 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.

flip_axis_to_camera Ran
ran, honoured the contract we drafted
matthewdm0816/bridgeqa/lib/ap_helper.py
pointer only (licence: NONE); the stored copy get_code serves, from tingxueronghua/dpke, is pointer only (licence: NONE) · get_code("eddd23cbbb297813")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, matthewdm0816/bridgeqa 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.

flip_axis_to_depth Ran
ran, honoured the contract we drafted
matthewdm0816/bridgeqa/lib/ap_helper.py
pointer only (licence: NONE) · get_code("d638b0201b9a9ece")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, matthewdm0816/bridgeqa 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.

get_answer_score Ran
ran, honoured the contract we drafted
matthewdm0816/bridgeqa/lib/dataset.py
pointer only (licence: NOASSERTION) · get_code("1fa1f4c088979cd4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, matthewdm0816/bridgeqa (NOASSERTION). 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.

is_dummy Ran
ran, violated the contract we drafted
matthewdm0816/bridgeqa/eval_scene_best_views.py
pointer only (licence: NOASSERTION) · get_code("a0958108a7e9ed33")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, matthewdm0816/bridgeqa (NOASSERTION). 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.

l1_loss Ran
ran; our contract draft was wrong, not the code
matthewdm0816/bridgeqa/lib/loss.py
pointer only (licence: NONE) · get_code("e1e4a142a595bcf2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, matthewdm0816/bridgeqa 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.

prep_ans Ran
ran; our contract draft was wrong, not the code
matthewdm0816/bridgeqa/lib/qa_helper.py
pointer only (licence: NONE); the stored copy get_code serves, from betterzh/sevlm-code, is pointer only (licence: NONE) · get_code("a9ad469e43133558")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, matthewdm0816/bridgeqa 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.

process_digit_article Ran
ran; our contract draft was wrong, not the code
matthewdm0816/bridgeqa/lib/qa_helper.py
pointer only (licence: NONE); the stored copy get_code serves, from betterzh/sevlm-code, is pointer only (licence: NONE) · get_code("1f4e29c084d8fb7a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, matthewdm0816/bridgeqa 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.

process_punctuation Ran
ran; our contract draft was wrong, not the code
matthewdm0816/bridgeqa/lib/qa_helper.py
pointer only (licence: NONE); the stored copy get_code serves, from betterzh/sevlm-code, is pointer only (licence: NONE) · get_code("ad323281cc450ace")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, matthewdm0816/bridgeqa 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.

smoothl1_loss Ran
ran; our contract draft was wrong, not the code
matthewdm0816/bridgeqa/lib/loss.py
pointer only (licence: NOASSERTION) · get_code("fe7609e5999f907d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, matthewdm0816/bridgeqa (NOASSERTION). 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.

softmax Ran
ran, honoured the contract we drafted
matthewdm0816/bridgeqa/lib/ap_helper.py
pointer only (licence: NONE) · get_code("1a034a72c15f9903")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, matthewdm0816/bridgeqa 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.

create_enet_for_3d Not yet run
unverified (harvested, no recorded run)
matthewdm0816/bridgeqa/lib/enet.py
pointer only (licence: NOASSERTION) · get_code("f9f6ab5de42cc2d4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, matthewdm0816/bridgeqa (NOASSERTION). 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 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 0 the same month, 3 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
flip_axis_to_camera 10 other papers
8 dated earlier, 2 later
1904.09664 (2019-04)
Deep Hough Voting for 3D Object Detection in Point Clouds
1912.11803 (2019-12)
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
2004.05679 (2020-04)
MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
and 7 more not named here
softmax 9 other papers
7 dated earlier, 2 later
1904.09664 (2019-04)
Deep Hough Voting for 3D Object Detection in Point Clouds
1912.11803 (2019-12)
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
2004.05679 (2020-04)
MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
and 6 more not named here
flip_axis_to_depth 7 other papers
5 dated earlier, 2 later
1904.09664 (2019-04)
Deep Hough Voting for 3D Object Detection in Point Clouds
1912.11803 (2019-12)
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
2203.05203 (2022-03)
MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes
and 4 more not named here
create_enet 2 other papers
2 dated earlier
2203.05203 (2022-03)
MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes
2204.06272 (2022-04)
3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
create_enet_for_3d 2 other papers
2 dated earlier
2203.05203 (2022-03)
MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes
2204.06272 (2022-04)
3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
l1_loss 2 other papers
2 dated earlier
2203.05238 (2022-03)
Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement
2204.06272 (2022-04)
3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
smoothl1_loss 2 other papers
2 dated earlier
2203.05238 (2022-03)
Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement
2204.06272 (2022-04)
3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
construct_bbox_corners 1 other paper
1 dated earlier
2204.06272 (2022-04)
3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
prep_ans 1 other paper
1 dated earlier
2101.07396 (2021-01)
ArtEmis: Affective Language for Visual Art
process_digit_article 1 other paper
1 dated earlier
2101.07396 (2021-01)
ArtEmis: Affective Language for Visual Art
process_punctuation 1 other paper
1 dated earlier
2101.07396 (2021-01)
ArtEmis: Affective Language for Visual Art

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

In 3D Visual Question Answering (3D VQA), the scarcity of fully annotated data and limited visual content diversity hampers the generalization to novel scenes and 3D concepts (e.g., only around 800 scenes are utilized in ScanQA and SQA dataset). Current approaches resort supplement 3D reasoning with 2D information. However, these methods face challenges: either they use top-down 2D views that introduce overly complex and sometimes question-irrelevant visual clues, or they rely on globally aggregated scene/imagelevel representations from 2D VLMs, losing the fine-grained vision-language correlations. To overcome these limitations, our approach utilizes question-conditional 2D view selection procedure, pinpointing semantically relevant 2D inputs for crucial visual clues. We then integrate this 2D knowledge into the 3D-VQA system via a two-branch Transformer structure. This structure, featuring a Twin-Transformer design, compactly combines 2D and 3D modalities and captures fine-grained correlations between modalities, allowing them mutually augmenting each other. Integrating proposed mechanisms above, we present BridgeQA, that offers a fresh perspective on multi-modal transformer-based architectures for 3D-VQA. Experiments validate that BridgeQA achieves state-of-the-art on 3D-VQA datasets and significantly outperforms existing solutions. Code is available at https://github. com/matthewdm0816/BridgeQA.

For agents

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

get_harvested_code_for_paper("2402.15933")
get_code_for_paper("2402.15933")
have("2402.15933")

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

curl https://syntology.ai/api/ran/2402.15933.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.15933.svg)](https://syntology.ai/paper/2402.15933)

Connect an agent — have() is free.