five

remyxai/OpenSpaces

收藏
Hugging Face2024-10-25 更新2025-04-12 收录
下载链接:
https://hf-mirror.com/datasets/remyxai/OpenSpaces
下载链接
链接失效反馈
官方服务:
资源简介:
--- license: apache-2.0 size_categories: - 1K<n<10K task_categories: - visual-question-answering - depth-estimation pretty_name: OpenSpaces dataset_info: features: - name: images sequence: image - name: messages list: - name: content list: - name: index dtype: int64 - name: text dtype: string - name: type dtype: string - name: role dtype: string splits: - name: train num_bytes: 1139972963.3616219 num_examples: 9255 - name: test num_bytes: 126745778.42237805 num_examples: 1029 download_size: 1260277343 dataset_size: 1266718741.784 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* tags: - vqasynth - remyx --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/647777304ae93470ffc28913/9igqva2qtGYcgQhwsXB3N.png) # OpenSpaces The OpenSpaces dataset is created using [VQASynth](https://github.com/remyxai/VQASynth) to synthesize spatialVQA data using images from the first 30K rows of the localized narratives split of [the cauldron](https://huggingface.co/datasets/HuggingFaceM4/the_cauldron). Compared to the [related dataset](remyxai/vqasynth_spacellava) used to train SpaceLLaVA, the OpenSpaces emphasizes greater diversity in the image distribution instead of focusing on warehouse scenes. The following chart shows the distribution of images over tags labeled by CLIP embedding similarity: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/647777304ae93470ffc28913/Gu_N9T8UgoVLpAZ8Pmu9C.png) The OpenSpaces dataset also includes relatively more of the qualitative distance estimation queries than the quanlitative queries about the relative position of objects in a scene. This histogram shows the distribution of estimated distances between objects in the image scenes ![image/png](https://cdn-uploads.huggingface.co/production/uploads/647777304ae93470ffc28913/OQvP7FStHcPQsdEWbj3Wz.png) ## Citation ``` @article{chen2024spatialvlm, title = {SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities}, author = {Chen, Boyuan and Xu, Zhuo and Kirmani, Sean and Ichter, Brian and Driess, Danny and Florence, Pete and Sadigh, Dorsa and Guibas, Leonidas and Xia, Fei}, journal = {arXiv preprint arXiv:2401.12168}, year = {2024}, url = {https://arxiv.org/abs/2401.12168}, } @misc{VQASynth, author = {remyxai}, title = {VQASynth}, year = {2024}, note = {GitHub repository}, url = {https://github.com/remyxai/VQASynth/tree/main} } ```
提供机构:
remyxai
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作