Related papers: A Neuromorphic Dataset for Object Segmentation in …
We present the first event-based learning approach for motion segmentation in indoor scenes and the first event-based dataset - EV-IMO - which includes accurate pixel-wise motion masks, egomotion and ground truth depth. Our approach is…
Automatic detection and segmentation of objects in 2D and 3D microscopy data is important for countless biomedical applications. In the natural image domain, spatial embedding-based instance segmentation methods are known to yield…
We introduce a new image segmentation task, called Entity Segmentation (ES), which aims to segment all visual entities (objects and stuffs) in an image without predicting their semantic labels. By removing the need of class label…
Autonomous robotic manipulation in clutter is challenging. A large variety of objects must be perceived in complex scenes, where they are partially occluded and embedded among many distractors, often in restricted spaces. To tackle these…
This paper presents Ev-Layout, a novel large-scale event-based multi-modal dataset designed for indoor layout estimation and tracking. Ev-Layout makes key contributions to the community by: Utilizing a hybrid data collection platform (with…
Analyzing scenes thoroughly is crucial for mobile robots acting in different environments. Semantic segmentation can enhance various subsequent tasks, such as (semantically assisted) person perception, (semantic) free space detection,…
Aerial surveillance demands rapid and precise detection of moving objects in dynamic environments. Event cameras, which draw inspiration from biological vision systems, present a promising alternative to frame-based sensors due to their…
Leveraging multiple sensors enhances complex environmental perception and increases resilience to varying luminance conditions and high-speed motion patterns, achieving precise localization and mapping. This paper proposes, ECMD, an…
Neuromorphic sensors, specifically event cameras, revolutionize visual data acquisition by capturing pixel intensity changes with exceptional dynamic range, minimal latency, and energy efficiency, setting them apart from conventional…
Detecting 3D objects in point clouds plays a crucial role in autonomous driving systems. Recently, advanced multi-modal methods incorporating camera information have achieved notable performance. For a safe and effective autonomous driving…
High-quality and challenging event stream datasets play an important role in the design of an efficient event-driven mechanism that mimics the brain. Although event cameras can provide high dynamic range and low-energy event stream data,…
Event camera is a novel bio-inspired vision sensor that outputs event stream. In this paper, we propose a novel data fusion algorithm called EAS to fuse conventional intensity images with the event stream. The fusion result is applied to…
Event cameras are bio-inspired sensors that capture the per-pixel intensity changes asynchronously and produce event streams encoding the time, pixel position, and polarity (sign) of the intensity changes. Event cameras possess a myriad of…
This paper focuses on few-shot Sound Event Detection (SED), which aims to automatically recognize and classify sound events with limited samples. However, prevailing methods methods in few-shot SED predominantly rely on segment-level…
Deep learning inference that needs to largely take place on the 'edge' is a highly computational and memory intensive workload, making it intractable for low-power, embedded platforms such as mobile nodes and remote security applications.…
Event-based vision revolutionizes traditional image sensing by capturing asynchronous intensity variations rather than static frames, enabling ultrafast temporal resolution, sparse data encoding, and enhanced motion perception. While this…
We introduce PACE (Pose Annotations in Cluttered Environments), a large-scale benchmark designed to advance the development and evaluation of pose estimation methods in cluttered scenarios. PACE provides a large-scale real-world benchmark…
A key algorithm for understanding the world is material segmentation, which assigns a label (metal, glass, etc.) to each pixel. We find that a model trained on existing data underperforms in some settings and propose to address this with a…
We present PartNet: a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. Our dataset consists of 573,585 part instances over 26,671 3D models covering 24 object…
We present a new public dataset with a focus on simulating robotic vision tasks in everyday indoor environments using real imagery. The dataset includes 20,000+ RGB-D images and 50,000+ 2D bounding boxes of object instances densely captured…