AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

3D-Aware Visual Question Answering about Parts, Poses and Occlusions

Xingrui Wang, Wufei Ma, Zhuowan Li, Adam Kortylewski, Alan Yuille

NeurIPS 2023 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use mesh projection to locate parts and occlusions instead of 2D part boxes (ablation)PNSVQA · Super-CLEVR-3D test (all question types)accuracy: 64.39 -> 68.15Improved
Use mesh projection to locate parts and occlusions instead of 2D part boxes (ablation)PNSVQA · Super-CLEVR-3D test (part questions)accuracy: 50.61 -> 56.30Improved
Use mesh projection to locate parts and occlusions instead of 2D part boxes (ablation)PNSVQA · Super-CLEVR-3D test (pose questions)accuracy: 87.78 -> 86.70Hurt
Use mesh projection to locate parts and occlusions instead of 2D part boxes (ablation)PNSVQA · Super-CLEVR-3D test (occlusion questions)accuracy: 65.80 -> 70.70Improved
Replace regression-based pose prediction with generative render-and-compare 6D pose estimation (ablation)PNSVQA+Projection · Super-CLEVR-3D test (all question types)accuracy: 68.15 -> 75.64Improved
Replace regression-based pose prediction with generative render-and-compare 6D pose estimation (ablation)PNSVQA+Projection · Super-CLEVR-3D test (part questions)accuracy: 56.30 -> 71.85Improved
Replace regression-based pose prediction with generative render-and-compare 6D pose estimation (ablation)PNSVQA+Projection · Super-CLEVR-3D test (pose questions)accuracy: 86.70 -> 86.40Hurt
Replace regression-based pose prediction with generative render-and-compare 6D pose estimation (ablation)PNSVQA+Projection · Super-CLEVR-3D test (occlusion questions)accuracy: 70.70 -> 76.90Improved
Replace regression-based pose prediction with generative render-and-compare 6D pose estimation (ablation)PNSVQA+Projection · Super-CLEVR-3D test (part+occlusion questions)accuracy: 58.90 -> 67.40Improved
Use PO3D-VQA's 3D-aware scene parsing and probabilistic modular reasoning instead of PNSVQA's 2D parsingPNSVQA · Super-CLEVR-3D test (all question types)accuracy: 64.39 -> 75.64Improved
Use PO3D-VQA instead of PNSVQAPNSVQA · Super-CLEVR-3D test (pose questions)accuracy: 87.78 -> 86.40Hurt
Use PO3D-VQA instead of PNSVQAPNSVQA · Super-CLEVR-3D test (part questions)accuracy: 50.61 -> 71.85Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy