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

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

24 Feb 2024arXiv:2402.15933archive 2025-07-28

Wentao Mo, Yang Liu

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/image-level 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 $\href{https://github.com/matthewdm0816/BridgeQA}{\text{this URL}}$.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.15933")

Code

Syntology Ran 10 of 13 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · honoured contract; 4 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

matthewdm0816/bridgeqa officialmentioned in paperpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested; 10 ran; 1 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
4ran · our draft was wrong
5ran
3unverified

Licence: 13 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from matthewdm0816/bridgeqa. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

construct_bbox_corners matthewdm0816/bridgeqa/lib/eval_helper.py official repository ran fingerprinted licence not identified · pointer only · c1a3575f07494487 · report
create_enet matthewdm0816/bridgeqa/lib/enet.py official repository ran licence not identified · pointer only · d209e4ea51338ac8 · report
flip_axis_to_camera matthewdm0816/bridgeqa/lib/ap_helper.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · eddd23cbbb297813 · report
get_answer_score matthewdm0816/bridgeqa/lib/dataset.py official repository ran fingerprinted licence not identified · pointer only · 1fa1f4c088979cd4 · report
is_dummy matthewdm0816/bridgeqa/eval_scene_best_views.py official repository ran fingerprinted licence not identified · pointer only · a0958108a7e9ed33 · report
l1_loss matthewdm0816/bridgeqa/lib/loss.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · e1e4a142a595bcf2 · report
prep_ans matthewdm0816/bridgeqa/lib/qa_helper.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · a9ad469e43133558 · report
process_digit_article matthewdm0816/bridgeqa/lib/qa_helper.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 1f4e29c084d8fb7a · report
process_punctuation matthewdm0816/bridgeqa/lib/qa_helper.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · ad323281cc450ace · report
smoothl1_loss matthewdm0816/bridgeqa/lib/loss.py official repository ran fingerprinted licence not identified · pointer only · fe7609e5999f907d · report
create_enet_for_3d matthewdm0816/bridgeqa/lib/enet.py official repository unverified licence not identified · pointer only · f9f6ab5de42cc2d4 · report
flip_axis_to_depth matthewdm0816/bridgeqa/lib/ap_helper.py official repository unverified no licence file found · pointer only · d638b0201b9a9ece · report
softmax matthewdm0816/bridgeqa/lib/ap_helper.py official repository unverified no licence file found · pointer only · 1a034a72c15f9903 · report

Tasks

3D Question Answering (3D-QA)Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Question Answering (3D-QA) ScanQA Test w/ objects BridgeQA BLEU-1 34.49 #1 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects BridgeQA BLEU-4 24.06 #1 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects BridgeQA CIDEr 83.75 #1 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects BridgeQA Exact Match 31.29 #1 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects BridgeQA METEOR 16.51 #1 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects BridgeQA ROUGE 43.26 #1 of 18 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections