SOTAVerified|Agents Browse Leaderboard About

3D Object Captioning

3D object captioning involves generating a natural language description of an object, given its point cloud representation.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–7 of 7 papers

Title	Date	Tasks	Status	Hype
PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models	Mar 13, 2025	3D Object Captioning	—Unverified	0
MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation	Nov 26, 2024	3D dense captioning3D Object Captioning	CodeCode Available	0
MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors	May 2, 2024	3D Object Captioning3D Object Classification	CodeCode Available	2
View Selection for 3D Captioning via Diffusion Ranking	Apr 11, 2024	3D Object CaptioningHallucination	CodeCode Available	3
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction	Feb 27, 2024	3D geometry3D Object Captioning	CodeCode Available	3
PointLLM: Empowering Large Language Models to Understand Point Clouds	Aug 31, 2023	3D Object Captioning3D Object Classification	CodeCode Available	2
3D-LLM: Injecting the 3D World into Large Language Models	Jul 24, 2023	3D Object Captioning3D Question Answering (3D-QA)	CodeCode Available	3

Show:10 25 50

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	MiniGPT-3D	GPT-4	57.06	—	Unverified
2	ShapeLLM-13B	GPT-4	48.94	—	Unverified
3	PointLLM-13B V1.2	GPT-4	48.15	—	Unverified
4	ShapeLLM-7B	GPT-4	46.92	—	Unverified
5	PointLLM-7B V1.2	GPT-4	44.85	—	Unverified
6	3D-LLM	GPT-4	33.42	—	Unverified