OpenCodePapers

3d-question-answering-3d-qa-on-3d-mm-vet

Visual Question Answering (VQA)3D Question Answering (3D-QA)
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeOverall AccuracyModelNameReleaseDate
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction✓ Link53.1ShapeLLM-13B2024-02-27
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction✓ Link47.4ShapeLLM-7B2024-02-27
PointLLM: Empowering Large Language Models to Understand Point Clouds✓ Link46.6PointLLM-13B v1.22023-08-31
PointLLM: Empowering Large Language Models to Understand Point Clouds✓ Link41.2PointLLM-7B v1.22023-08-31
Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following✓ Link23.5Point-Bind & Point-LLM2023-09-01