Visual Question Answering (VQA) on ScanQA Test w/ objects

Metric: METEOR (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	METEOR▼	Extra Data	Paper	Date↕	Code
1	LLaVA-3D	20.8	No	LLaVA-3D: A Simple yet Effective Pathway to Empo...	2024-09-26	-
2	LEO	20	No	An Embodied Generalist Agent in 3D World	2023-11-18	Code
3	ChatScene	18	No	Chat-Scene: Bridging 3D Scene and Large Language...	2023-12-13	Code
4	Scene-LLM	16.6	No	Scene-LLM: Extending Language Model for 3D Visua...	2024-03-18	-
5	NaviLLM	16.56	No	Towards Learning a Generalist Model for Embodied...	2023-12-04	Code
6	BridgeQA	16.51	No	Bridging the Gap between 2D and 3D Visual Questi...	2024-02-24	Code
7	LL3DA	15.9	No	Visual Instruction Tuning	2023-04-17	Code
8	3D-LLM (BLIP2-flant5)	14.9	No	3D-LLM: Injecting the 3D World into Large Langua...	2023-07-24	Code
9	3D-LLM (BLIP2-opt)	14.3	No	3D-LLM: Injecting the 3D World into Large Langua...	2023-07-24	Code
10	3D-VisTA	13.9	No	3D-VisTA: Pre-trained Transformer for 3D Vision ...	2023-08-08	Code
11	ScanQA	13.55	No	ScanQA: 3D Question Answering for Spatial Scene ...	2021-12-20	Code
12	3D-LLM (flamingo)	13.5	No	3D-LLM: Injecting the 3D World into Large Langua...	2023-07-24	Code
13	VoteNet+MCAN	12.07	No	ScanQA: 3D Question Answering for Spatial Scene ...	2021-12-20	Code
14	ScanRefer+MCAN	11.97	No	ScanQA: 3D Question Answering for Spatial Scene ...	2021-12-20	Code
15	VideoChat2	9.5	No	MVBench: A Comprehensive Multi-modal Video Under...	2023-11-28	Code
16	LLaVA-NeXT-Video	9.1	No	LLaVA-OneVision: Easy Visual Task Transfer	2024-08-06	Code

#1LLaVA-3DSOTA
20.8
METEOR· 2024-09-26
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness
#2LEOSOTA
20
METEOR· 2023-11-18
An Embodied Generalist Agent in 3D World Code
#3ChatScene
18
METEOR· 2023-12-13
Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers Code
#4Scene-LLM
16.6
METEOR· 2024-03-18
Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning
#5NaviLLM
16.56
METEOR· 2023-12-04
Towards Learning a Generalist Model for Embodied Navigation Code
#6BridgeQA
16.51
METEOR· 2024-02-24
Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA Code
#7LL3DASOTA
15.9
METEOR· 2023-04-17
Visual Instruction Tuning Code
#83D-LLM (BLIP2-flant5)
14.9
METEOR· 2023-07-24
3D-LLM: Injecting the 3D World into Large Language Models Code
#93D-LLM (BLIP2-opt)
14.3
METEOR· 2023-07-24
3D-LLM: Injecting the 3D World into Large Language Models Code
#103D-VisTA
13.9
METEOR· 2023-08-08
3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment Code
#11ScanQASOTA
13.55
METEOR· 2021-12-20
ScanQA: 3D Question Answering for Spatial Scene Understanding Code
#123D-LLM (flamingo)
13.5
METEOR· 2023-07-24
3D-LLM: Injecting the 3D World into Large Language Models Code
#13VoteNet+MCAN
12.07
METEOR· 2021-12-20
ScanQA: 3D Question Answering for Spatial Scene Understanding Code
#14ScanRefer+MCAN
11.97
METEOR· 2021-12-20
ScanQA: 3D Question Answering for Spatial Scene Understanding Code
#15VideoChat2
9.5
METEOR· 2023-11-28
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark Code
#16LLaVA-NeXT-Video
9.1
METEOR· 2024-08-06
LLaVA-OneVision: Easy Visual Task Transfer Code