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

Metric: ROUGE (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	ROUGE▼	Extra Data	Paper	Date↕	Code
1	LLaVA-3D	49.6	No	LLaVA-3D: A Simple yet Effective Pathway to Empo...	2024-09-26	-
2	LEO	49.2	No	An Embodied Generalist Agent in 3D World	2023-11-18	Code
3	BridgeQA	43.26	No	Bridging the Gap between 2D and 3D Visual Questi...	2024-02-24	Code
4	ChatScene	41.6	No	Chat-Scene: Bridging 3D Scene and Large Language...	2023-12-13	Code
5	NaviLLM	40.23	No	Towards Learning a Generalist Model for Embodied...	2023-12-04	Code
6	Scene-LLM	40	No	Scene-LLM: Extending Language Model for 3D Visua...	2024-03-18	-
7	LL3DA	37.3	No	Visual Instruction Tuning	2023-04-17	Code
8	3D-VisTA	35.7	No	3D-VisTA: Pre-trained Transformer for 3D Vision ...	2023-08-08	Code
9	3D-LLM (BLIP2-flant5)	35.3	No	3D-LLM: Injecting the 3D World into Large Langua...	2023-07-24	Code
10	3D-LLM (flamingo)	34.8	No	3D-LLM: Injecting the 3D World into Large Langua...	2023-07-24	Code
11	3D-LLM (BLIP2-opt)	34.5	No	3D-LLM: Injecting the 3D World into Large Langua...	2023-07-24	Code
12	ScanQA	34.34	No	ScanQA: 3D Question Answering for Spatial Scene ...	2021-12-20	Code
13	VoteNet+MCAN	30.97	No	ScanQA: 3D Question Answering for Spatial Scene ...	2021-12-20	Code
14	ScanRefer+MCAN	30.68	No	ScanQA: 3D Question Answering for Spatial Scene ...	2021-12-20	Code
15	VideoChat2	28.2	No	MVBench: A Comprehensive Multi-modal Video Under...	2023-11-28	Code
16	LLaVA-NeXT-Video	27.8	No	LLaVA-OneVision: Easy Visual Task Transfer	2024-08-06	Code

#1LLaVA-3DSOTA
49.6
ROUGE· 2024-09-26
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness
#2LEOSOTA
49.2
ROUGE· 2023-11-18
An Embodied Generalist Agent in 3D World Code
#3BridgeQA
43.26
ROUGE· 2024-02-24
Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA Code
#4ChatScene
41.6
ROUGE· 2023-12-13
Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers Code
#5NaviLLM
40.23
ROUGE· 2023-12-04
Towards Learning a Generalist Model for Embodied Navigation Code
#6Scene-LLM
40
ROUGE· 2024-03-18
Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning
#7LL3DASOTA
37.3
ROUGE· 2023-04-17
Visual Instruction Tuning Code
#83D-VisTA
35.7
ROUGE· 2023-08-08
3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment Code
#93D-LLM (BLIP2-flant5)
35.3
ROUGE· 2023-07-24
3D-LLM: Injecting the 3D World into Large Language Models Code
#103D-LLM (flamingo)
34.8
ROUGE· 2023-07-24
3D-LLM: Injecting the 3D World into Large Language Models Code
#113D-LLM (BLIP2-opt)
34.5
ROUGE· 2023-07-24
3D-LLM: Injecting the 3D World into Large Language Models Code
#12ScanQASOTA
34.34
ROUGE· 2021-12-20
ScanQA: 3D Question Answering for Spatial Scene Understanding Code
#13VoteNet+MCAN
30.97
ROUGE· 2021-12-20
ScanQA: 3D Question Answering for Spatial Scene Understanding Code
#14ScanRefer+MCAN
30.68
ROUGE· 2021-12-20
ScanQA: 3D Question Answering for Spatial Scene Understanding Code
#15VideoChat2
28.2
ROUGE· 2023-11-28
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark Code
#16LLaVA-NeXT-Video
27.8
ROUGE· 2024-08-06
LLaVA-OneVision: Easy Visual Task Transfer Code