大模型推理能力 - arXivDaily 专题

2407.20727 2024-07-31 cs.CV 50%

SceneTeller: Language-to-3D Scene Generation

Başak Melis Öcal, Maxim Tatarchenko, Sezer Karaoglu, Theo Gevers

专题命中视觉空间推理：planning(abstract)

Comments ECCV'24 camera-ready version

2403.16921 2024-07-24 cs.CV 50%

PropTest: Automatic Property Testing for Improved Visual Programming

Jaywon Koo, Ziyan Yang, Paola Cascante-Bonilla, Baishakhi Ray, Vicente Ordonez

专题命中视觉空间推理：reasoning(abstract)

Comments Project Page: https://jaywonkoo17.github.io/PropTest/

2407.14758 2024-07-23 cs.CV 50%

DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control

Xinyu Xu, Shengcheng Luo, Yanchao Yang, Yong-Lu Li, Cewu Lu

专题命中视觉空间推理：planning(abstract)

Comments ECCV 2024

2401.18075 2024-07-23 cs.CV 50%

CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting

Jiezhi Yang, Khushi Desai, Charles Packer, Harshil Bhatia, Nicholas Rhinehart, Rowan McAllister, Joseph Gonzalez

专题命中视觉空间推理：planning(abstract)

Comments ECCV 2024. Project page with video and code: www.carff.website

2407.12435 2024-07-18 cs.CV 50%

F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions

Jie Yang, Xuesong Niu, Nan Jiang, Ruimao Zhang, Siyuan Huang

专题命中视觉空间推理：reasoning(abstract)

Comments ECCV24

2407.08931 2024-07-15 cs.CV 50%

Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection

Xingyu Peng, Yan Bai, Chen Gao, Lirong Yang, Fei Xia, Beipeng Mu, Xiaofei Wang, Si Liu

专题命中视觉空间推理：chain-of-thought(abstract)

Comments accepted by ECCV 2024

2407.04938 2024-07-15 cs.CV 50%

SAM-Med3D-MoE: Towards a Non-Forgetting Segment Anything Model via Mixture of Experts for 3D Medical Image Segmentation

Guoan Wang, Jin Ye, Junlong Cheng, Tianbin Li, Zhaolin Chen, Jianfei Cai, Junjun He, Bohan Zhuang

专题命中视觉空间推理：planning(abstract)

Journal ref MICCAI 2024

2403.14121 2024-07-11 cs.CV 50%

External Knowledge Enhanced 3D Scene Generation from Sketch

Zijie Wu, Mingtao Feng, Yaonan Wang, He Xie, Weisheng Dong, Bo Miao, Ajmal Mian

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted by ECCV2024

2402.06838 2024-07-09 cs.RO 50%

NavFormer: A Transformer Architecture for Robot Target-Driven Navigation in Unknown and Dynamic Environments

Haitong Wang, Aaron Hao Tan, Goldie Nejat

专题命中视觉空间推理：reasoning(abstract)

2407.02473 2024-07-03 cs.RO 50%

Open Scene Graphs for Open World Object-Goal Navigation

Joel Loo, Zhanxin Wu, David Hsu

专题命中视觉空间推理：reasoning(abstract)

2404.19379 2024-07-02 cs.CV cs.RO 50%

SemanticFormer: Holistic and Semantic Traffic Scene Representation for Trajectory Prediction using Knowledge Graphs

Zhigang Sun, Zixu Wang, Lavdim Halilaj, Juergen Luettin

专题命中视觉空间推理：reasoning(abstract)

Comments 8 pages, 7 figures, has been accepted for publication in the IEEE Robotics and Automation Letters (RA-L)

2310.04671 2024-07-02 cs.CV 50%

Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction

Korawat Charoenpitaks, Van-Quang Nguyen, Masanori Suganuma, Masahiro Takahashi, Ryoma Niihara, Takayuki Okatani

专题命中视觉空间推理：reasoning(abstract)

Comments Main Paper: 11 pages, Supplementary Materials: 25 pages

Journal ref IEEE Trans. Intell. Veh. (2024) 1-11

2406.20083 2024-07-01 cs.RO cs.CV 50%

PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators

Kuo-Hao Zeng, Zichen Zhang, Kiana Ehsani, Rose Hendrix, Jordi Salvador, Alvaro Herrasti, Ross Girshick, Aniruddha Kembhavi, Luca Weihs

专题命中视觉空间推理：reasoning(abstract)

2406.17151 2024-06-26 cs.RO 50%

Socially Acceptable Bipedal Robot Navigation via Social Zonotope Network Model Predictive Control

Abdulaziz Shamsah, Krishanu Agarwal, Nigam Katta, Abirath Raju, Shreyas Kousik, Ye Zhao

专题命中视觉空间推理：planning(abstract)

Comments 19 pages, 19 figures. arXiv admin note: text overlap with arXiv:2403.16485, arXiv:2310.09969

2311.17851 2024-06-18 cs.CV 50%

Leveraging VLM-Based Pipelines to Annotate 3D Objects

Rishabh Kabra, Loic Matthey, Alexander Lerchner, Niloy J. Mitra

专题命中视觉空间推理：reasoning(abstract)

2406.09613 2024-06-17 cs.CV 50%

ImageNet3D: Towards General-Purpose Object-Level 3D Understanding

Wufei Ma, Guanning Zeng, Guofeng Zhang, Qihao Liu, Letian Zhang, Adam Kortylewski, Yaoyao Liu, Alan Yuille

专题命中视觉空间推理：reasoning(abstract)

2406.07549 2024-06-14 cs.RO 50%

A3VLM: Actionable Articulation-Aware Vision Language Model

Siyuan Huang, Haonan Chang, Yuhan Liu, Yimeng Zhu, Hao Dong, Peng Gao, Abdeslam Boularias, Hongsheng Li

专题命中视觉空间推理：reasoning(abstract)

2406.07163 2024-06-12 cs.CV 50%

FaceGPT: Self-supervised Learning to Chat about 3D Human Faces

Haoran Wang, Mohit Mendiratta, Christian Theobalt, Adam Kortylewski

专题命中视觉空间推理：reasoning(abstract)

2303.01212 2024-06-11 cs.CV cs.RO 50%

Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review

Yining Shi, Kun Jiang, Jiusi Li, Zelin Qian, Junze Wen, Mengmeng Yang, Ke Wang, Diange Yang

专题命中视觉空间推理：planning(abstract)

2406.04983 2024-06-10 cs.CV 50%

CityCraft: A Real Crafter for 3D City Generation

Jie Deng, Wenhao Chai, Junsheng Huang, Zhonghan Zhao, Qixuan Huang, Mingyan Gao, Jianshu Guo, Shengyu Hao, Wenhao Hu, Jenq-Neng Hwang, Xi Li, Gaoang Wang

专题命中视觉空间推理：planning(abstract)

Comments 20 pages, 9 figures

2406.04659 2024-06-10 cs.CV 50%

LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model

Dongkai Wang, Shiyu Xuan, Shiliang Zhang

专题命中视觉空间推理：reasoning(abstract)

Comments CVPR2024

2406.04300 2024-06-07 cs.RO 50%

Text-to-Drive: Diverse Driving Behavior Synthesis via Large Language Models

Phat Nguyen, Tsun-Hsuan Wang, Zhang-Wei Hong, Sertac Karaman, Daniela Rus

专题命中视觉空间推理：reasoning(abstract)

Comments 14 pages, 7 figures

2406.03866 2024-06-07 cs.CV 50%

LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model

Yixuan Yang, Junru Lu, Zixiang Zhao, Zhen Luo, James J. Q. Yu, Victor Sanchez, Feng Zheng

专题命中视觉空间推理：planning(abstract)

2406.02425 2024-06-05 cs.CV cs.RO 50%

CoNav: A Benchmark for Human-Centered Collaborative Navigation

Changhao Li, Xinyu Sun, Peihao Chen, Jugang Fan, Zixu Wang, Yanxia Liu, Jinhui Zhu, Chuang Gan, Mingkui Tan

专题命中视觉空间推理：reasoning(abstract)

2312.04314 2024-06-04 cs.CV 50%

GPT4SGG: Synthesizing Scene Graphs from Holistic and Region-specific Narratives

Zuyao Chen, Jinlin Wu, Zhen Lei, Zhaoxiang Zhang, Changwen Chen

专题命中视觉空间推理：reasoning(abstract)

2405.16818 2024-05-28 cs.RO cs.HC 50%

Advancing Behavior Generation in Mobile Robotics through High-Fidelity Procedural Simulations

Victor A. Kich, Jair A. Bottega, Raul Steinmetz, Ricardo B. Grando, Ayanori Yorozu, Akihisa Ohya

专题命中视觉空间推理：reasoning(abstract)

Comments Preprint of 33rd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

2405.07784 2024-05-14 cs.CV 50%

Generating Human Motion in 3D Scenes from Text Descriptions

Zhi Cen, Huaijin Pi, Sida Peng, Zehong Shen, Minghui Yang, Shuai Zhu, Hujun Bao, Xiaowei Zhou

专题命中视觉空间推理：reasoning(abstract)

Comments Project page: https://zju3dv.github.io/text_scene_motion

2405.07451 2024-05-14 cs.CV 50%

CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering

Yuanyuan Jiang, Jianqin Yin

专题命中视觉空间推理：reasoning(abstract)

Comments Submitted to the Journal on February 6, 2024

2404.00906 2024-04-25 cs.CV 50%

From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models

Rongjie Li, Songyang Zhang, Dahua Lin, Kai Chen, Xuming He

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted by CVPR 2024

2311.18836 2024-04-25 cs.CV 50%

ChatPose: Chatting about 3D Human Pose

Yao Feng, Jing Lin, Sai Kumar Dwivedi, Yu Sun, Priyanka Patel, Michael J. Black

专题命中视觉空间推理：reasoning(abstract)

Comments Home page: https://yfeng95.github.io/ChatPose/

1. 视觉空间推理 3363 篇

SceneTeller: Language-to-3D Scene Generation

PropTest: Automatic Property Testing for Improved Visual Programming

DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control

CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting

F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions

Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection

SAM-Med3D-MoE: Towards a Non-Forgetting Segment Anything Model via Mixture of Experts for 3D Medical Image Segmentation

External Knowledge Enhanced 3D Scene Generation from Sketch

NavFormer: A Transformer Architecture for Robot Target-Driven Navigation in Unknown and Dynamic Environments

Open Scene Graphs for Open World Object-Goal Navigation

SemanticFormer: Holistic and Semantic Traffic Scene Representation for Trajectory Prediction using Knowledge Graphs

Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction

PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators

Socially Acceptable Bipedal Robot Navigation via Social Zonotope Network Model Predictive Control

Leveraging VLM-Based Pipelines to Annotate 3D Objects

ImageNet3D: Towards General-Purpose Object-Level 3D Understanding

A3VLM: Actionable Articulation-Aware Vision Language Model

FaceGPT: Self-supervised Learning to Chat about 3D Human Faces

Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review

CityCraft: A Real Crafter for 3D City Generation

LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model

Text-to-Drive: Diverse Driving Behavior Synthesis via Large Language Models

LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model

CoNav: A Benchmark for Human-Centered Collaborative Navigation

GPT4SGG: Synthesizing Scene Graphs from Holistic and Region-specific Narratives

Advancing Behavior Generation in Mobile Robotics through High-Fidelity Procedural Simulations

Generating Human Motion in 3D Scenes from Text Descriptions

CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering

From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models

ChatPose: Chatting about 3D Human Pose