Cooking beyond Frames: A Stereo Event Camera Dataset in the Kitchen

• URL: http://arxiv.org/abs/2608.04865v1
• Date: Wed, 05 Aug 2026 13:59:01 GMT
• Title: Cooking beyond Frames: A Stereo Event Camera Dataset in the Kitchen
• Abstract summary: We introduce EventKitchen, a large-scale stereo event camera benchmark dataset of human cooking activities in the kitchen.<n>EventKitchen comprises 5.5 hours of stereo event recordings with synchronized RGB, depth, and IMU data.<n>We train baseline models on EventKitchen to perform multiple event-based tasks, including action recognition, object detection, and stereo depth estimation.
• Score: 13.51664777359244
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Event cameras, also known as neuromorphic cameras, have gained significant attention in recent years due to their high temporal resolution, high dynamic range, and low power consumption. While many studies and datasets in neuromorphic vision have focused on automotive and drone applications, human-centric daily-life scenarios remain largely underrepresented, despite their importance for developing and benchmarking event-based perception systems. Moreover, the few existing event-based human activity datasets are typically recorded with scripted human actions, limiting their ability to capture natural human behaviors. In this paper, we introduce EventKitchen, a large-scale stereo event camera benchmark dataset of human cooking activities in the kitchen. EventKitchen is egocentrically collected from 10 participants in 13 diverse kitchens, where the participants wear a helmet with multiple sensors and naturally perform cooking activities, without any scripted actions. EventKitchen comprises 5.5 hours of stereo event recordings with synchronized RGB, depth, and IMU data. We provide human annotations for 10,762 action segments and 13,482 bounding boxes. We train baseline models on EventKitchen to perform multiple event-based tasks, including action recognition, object detection, and stereo depth estimation. By capturing natural, real-world human activities, EventKitchen establishes a challenging benchmark for neuromorphic vision beyond autonomous driving.

Related papers

• Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset [64.37557018733408]
  Embody 3D is a multimodal dataset of 500 individual hours of 3D motion data from 439 participants collected in a multi-camera collection stage.<n>The dataset features a wide range of single-person motion data, including prompted motions, hand gestures, and locomotion.<n>We provide tracked human motion including hand tracking and body shape, text annotations, and a separate audio track for each participant.
  arXiv  Detail & Related papers  (2025-10-17T23:06:36Z)
• EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models [69.44009961659668]
  We introduce the EPFL-Smart-Kitchen-30 dataset, collected in a motion capture platform inside a kitchen environment.<n>Nine static RGB-D cameras, inertial measurement units (IMUs) and one head-mounted HoloLens2 headset were used to capture 3D hand, body, and eye movements.<n>The dataset is a multi-view action dataset with synchronized exocentric, egocentric, depth, IMUs, eye gaze, body and hand kinematics spanning 29.7 hours of 16 subjects cooking four different recipes.
  arXiv  Detail & Related papers  (2025-06-02T12:46:44Z)
• EventEgoHands: Event-based Egocentric 3D Hand Mesh Reconstruction [2.3695551082138864]
  Reconstructing 3D hand mesh is challenging but an important task for human-computer interaction and AR/VR applications.<n>We propose EventEgoHands, a novel method for event-based 3D hand mesh reconstruction in an egocentric view.<n>Our approach introduces a Hand Module that extracts hand regions, effectively mitigating the influence of dynamic background events.
  arXiv  Detail & Related papers  (2025-05-25T14:36:51Z)
• EventEgo3D++: 3D Human Motion Capture from a Head-Mounted Event Camera [64.58147600753382]
  EventEgo3D++ is a monocular event camera with a fisheye lens for 3D human motion capture.<n>Event cameras excel in high-speed scenarios and varying illumination due to their high temporal resolution.<n>Our method supports real-time 3D pose updates at a rate of 140Hz.
  arXiv  Detail & Related papers  (2025-02-11T18:57:05Z)
• EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams [59.77837807004765]
  This paper introduces a new problem, i.e., 3D human motion capture from an egocentric monocular event camera with a fisheye lens. Event streams have high temporal resolution and provide reliable cues for 3D human motion capture under high-speed human motions and rapidly changing illumination. Our EE3D demonstrates robustness and superior 3D accuracy compared to existing solutions while supporting real-time 3D pose update rates of 140Hz.
  arXiv  Detail & Related papers  (2024-04-12T17:59:47Z)
• Exploring Event-based Human Pose Estimation with 3D Event Representations [26.34100847541989]
  We introduce two 3D event representations: the Rasterized Event Point Cloud (Ras EPC) and the Decoupled Event Voxel (DEV) The Ras EPC aggregates events within concise temporal slices at identical positions, preserving their 3D attributes along with statistical information, thereby significantly reducing memory and computational demands. Our methods are tested on the DHP19 public dataset, MMHPSD dataset, and our EV-3DPW dataset, with further qualitative validation via a derived driving scene dataset EV-JAAD and an outdoor collection vehicle.
  arXiv  Detail & Related papers  (2023-11-08T10:45:09Z)
• Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events [106.19047816743988]
  We present a new large-scale dataset with comprehensive annotations, named Human-in-Events or HiEve. It contains a record number of poses (>1M), the largest number of action instances (>56k) under complex events, as well as one of the largest numbers of trajectories lasting for longer time. Based on its diverse annotation, we present two simple baselines for action recognition and pose estimation.
  arXiv  Detail & Related papers  (2020-05-09T18:24:52Z)
• The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines [88.47608066382267]
  We detail how this large-scale dataset was captured by 32 participants in their native kitchen environments. Recording took place in 4 countries by participants belonging to 10 different nationalities. Our dataset features 55 hours of video consisting of 11.5M frames, which we densely labelled for a total of 39.6K action segments and 454.2K object bounding boxes.
  arXiv  Detail & Related papers  (2020-04-29T21:57:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.