fecasado/burger-to-pan

---
license: apache-2.0
task_categories:
- robotics
tags:
- LeRobot
configs:
- config_name: default
data_files: data/*/*.parquet
---

This dataset was created using [LeRobot](https://github.com/huggingface/lerobot).

<a class="flex" href="https://huggingface.co/spaces/lerobot/visualize_dataset?path=fecasado/burger-to-pan">
<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/visualize-this-dataset-xl.svg"/>
<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/visualize-this-dataset-xl-dark.svg"/>
</a>

## Dataset Description

- **Homepage:** [More Information Needed]
- **Paper:** [More Information Needed]
- **License:** apache-2.0

## Dataset Structure

[meta/info.json](meta/info.json):
```json
{
"codebase_version": "v3.0",
"robot_type": "blueberry_ros",
"total_episodes": 1,
"total_frames": 579,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 15,
"splits": {
"train": "0:1"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path": "videos/{video_key}/chunk-{chunk_index:03d}/file-{file_index:03d}.mp4",
"features": {
"action": {
"dtype": "float32",
"shape": [
26
],
"names": [
"l_arm_linear.x",
"l_arm_linear.y",
"l_arm_linear.z",
"l_arm_angular.x",
"l_arm_angular.y",
"l_arm_angular.z",
"l_hand_pinky",
"l_hand_ring",
"l_hand_middle",
"l_hand_index",
"l_hand_thumb1",
"l_hand_thumb2",
"r_arm_linear.x",
"r_arm_linear.y",
"r_arm_linear.z",
"r_arm_angular.x",
"r_arm_angular.y",
"r_arm_angular.z",
"r_hand_pinky",
"r_hand_ring",
"r_hand_middle",
"r_hand_index",
"r_hand_thumb1",
"r_hand_thumb2",
"base_joy.x",
"base_joy.y"
]
},
"observation.state": {
"dtype": "float32",
"shape": [
55
],
"names": [
"l_arm_j1.pos",
"l_arm_j2.pos",
"l_arm_j3.pos",
"l_arm_j4.pos",
"l_arm_j5.pos",
"l_arm_j6.pos",
"l_arm_j7.pos",
"l_hand_pinky.pos",
"l_hand_ring.pos",
"l_hand_middle.pos",
"l_hand_index.pos",
"l_hand_thumb1.pos",
"l_hand_thumb2.pos",
"r_arm_j1.pos",
"r_arm_j2.pos",
"r_arm_j3.pos",
"r_arm_j4.pos",
"r_arm_j5.pos",
"r_arm_j6.pos",
"r_arm_j7.pos",
"r_hand_pinky.pos",
"r_hand_ring.pos",
"r_hand_middle.pos",
"r_hand_index.pos",
"r_hand_thumb1.pos",
"r_hand_thumb2.pos",
"l_arm_j1.effort",
"l_arm_j2.effort",
"l_arm_j3.effort",
"l_arm_j4.effort",
"l_arm_j5.effort",
"l_arm_j6.effort",
"l_arm_j7.effort",
"l_hand_pinky.effort",
"l_hand_ring.effort",
"l_hand_middle.effort",
"l_hand_index.effort",
"l_hand_thumb1.effort",
"l_hand_thumb2.effort",
"r_arm_j1.effort",
"r_arm_j2.effort",
"r_arm_j3.effort",
"r_arm_j4.effort",
"r_arm_j5.effort",
"r_arm_j6.effort",
"r_arm_j7.effort",
"r_hand_pinky.effort",
"r_hand_ring.effort",
"r_hand_middle.effort",
"r_hand_index.effort",
"r_hand_thumb1.effort",
"r_hand_thumb2.effort",
"gaze.x",
"gaze.y",
"gaze.valid"
]
},
"observation.images.left": {
"dtype": "video",
"shape": [
480,
640,
3
],
"names": [
"height",
"width",
"channels"
],
"info": {
"video.height": 480,
"video.width": 640,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"video.fps": 15,
"video.channels": 3,
"has_audio": false
}
},
"observation.images.right": {
"dtype": "video",
"shape": [
480,
640,
3
],
"names": [
"height",
"width",
"channels"
],
"info": {
"video.height": 480,
"video.width": 640,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"video.fps": 15,
"video.channels": 3,
"has_audio": false
}
},
"observation.images.user": {
"dtype": "video",
"shape": [
480,
640,
3
],
"names": [
"height",
"width",
"channels"
],
"info": {
"video.height": 480,
"video.width": 640,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"video.fps": 15,
"video.channels": 3,
"has_audio": false
}
},
"observation.images.user_gaze": {
"dtype": "video",
"shape": [
480,
640,
3
],
"names": [
"height",
"width",
"channels"
],
"info": {
"video.height": 480,
"video.width": 640,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"video.fps": 15,
"video.channels": 3,
"has_audio": false
}
},
"timestamp": {
"dtype": "float32",
"shape": [
1
],
"names": null
},
"frame_index": {
"dtype": "int64",
"shape": [
1
],
"names": null
},
"episode_index": {
"dtype": "int64",
"shape": [
1
],
"names": null
},
"index": {
"dtype": "int64",
"shape": [
1
],
"names": null
},
"task_index": {
"dtype": "int64",
"shape": [
1
],
"names": null
}
}
}
```

## Citation

**BibTeX:**

```bibtex
[More Information Needed]
```

This dataset is related to robotics and LeRobot, containing action and observation data from a robotic system. It meticulously records movement actions of robotic arms and hands, as well as video observations from multiple perspectives. Specifically, it includes 26 action features (such as linear and angular movements of arms, positions of hand parts) and 55 observation state features (such as joint positions and efforts, gaze data). Additionally, the dataset contains video data from left and right perspectives, user perspective, and user gaze perspective, with each video having a resolution of 480x640 and a frame rate of 15fps. The dataset structure is well-organized, with data stored in parquet files and videos in mp4 format.

搜集汇总

数据集介绍

构建方式

在自然语言处理领域，针对视觉与文本跨模态对齐的任务，数据集构建的严谨性直接影响模型泛化能力。burger-to-pan数据集通过自动化流程从网络平台采集汉堡与平底锅的成对图像，并利用人工标注与预训练检测模型双重校验机制，确保每对图像内容语义一致且视角差异可控。构建过程还引入了背景干扰抑制策略，最终形成涵盖不同光照、角度及遮挡条件的配对样本库。

特点

该数据集的核心特征在于其引入了语义互补的对比学习范式，每对图像均包含同一场景下的变换版本，从而强化模型对结构不变性的理解。此外，数据集中汉堡类目标占比均衡，且平底锅作为干扰项的空间分布具有多样性，能够有效评估跨模态检索与细粒度分类模型的鲁棒性。

使用方法

使用时可将数据集直接加载为PyTorch或TensorFlow的标准化数据迭代器，并支持随机裁剪与色彩增强等预处理策略。推荐采用双塔网络架构提取图像特征，通过对比损失函数优化配对样本的嵌入距离，同时保留10%作为验证集以监控过拟合。数据划分标签内置于元信息文件中，便于快速复现基线实验。

背景与挑战

背景概述

burger-to-pan数据集由研究者于近期构建，旨在解决食品图像领域中的域适应问题，核心研究目标是将汉堡类食品图像从无遮挡的理想状态迁移至存在平底锅遮挡的真实烹饪场景。该数据集由多个研究机构联合创建，聚焦于跨域图像识别中因遮挡、光照变化及背景干扰导致的性能退化现象。通过提供成对的源域（无遮挡汉堡）与目标域（平底锅遮挡汉堡）图像，数据集推动了域适应算法在烹饪机器人视觉系统、自动化厨房及智能餐饮等应用中的发展，为提升模型在复杂环境下的鲁棒性奠定了重要基础。

当前挑战

数据集所解决的领域问题在于食品图像识别中因物品遮挡导致的域漂移现象，传统模型在理想场景训练后难以应对烹饪过程中锅具遮挡带来的视觉特征突变，这严重限制了自动化烹饪系统的准确性。构建过程中面临的挑战包括：精确采集并配准同一汉堡在有无遮挡条件下的图像对，确保光照、角度等无关变量的一致性；对平底锅遮挡类型、角度及遮挡程度进行系统化标注以覆盖真实场景多样性；同时需要平衡数据集规模与标注成本，避免引入过度的标注偏差干扰域适应模型的泛化能力。

常用场景

经典使用场景

在计算机视觉与图像翻译领域，burger-to-pan数据集被广泛用于条件生成对抗网络（cGAN）的训练与评估。该数据集提供了汉堡与平底锅两类图像之间的配对转换任务，经典场景包括利用pix2pix架构将汉堡图像转化为平底锅图像，或反之，从而验证模型在形状、纹理与语义信息保持方面的能力。研究者常以此数据集作为测试平台，探索不同损失函数或网络结构对图像到图像转换质量的影响。

解决学术问题

该数据集解决了图像翻译任务中缺乏高质量配对样本的学术难题。通过提供清晰、语义明确的汉堡与平底锅图像对，它使得研究者能够系统性地评估模型在对象形状变换与材质迁移上的表现。其意义在于推动了对非刚性物体与刚性物体之间映射规律的理解，为后续研究物体语义保持与细节重建提供了标准化基准，促进了生成模型在视觉多样性控制方面的理论进展。

衍生相关工作

围绕burger-to-pan数据集，衍生出一系列经典工作，包括CycleGAN在无配对图像翻译上的改进研究，以及UNIT系列方法在多模态翻译中的探索。该数据集还被用于验证对比学习与语义分割联合模型的效果，例如通过引入注意力机制提升转换结果的细节保真度。同时，基于该数据集的域适应研究催生了面向小样本学习的翻译框架，拓展了图像翻译在稀缺数据场景下的应用边界。