Related papers: CoDEPS: Online Continual Learning for Depth Estima…
Self-supervised monocular depth estimation networks are trained to predict scene depth using nearby frames as a supervision signal during training. However, for many applications, sequence information in the form of video frames is also…
Many deep learning based automated medical image segmentation systems, in reality, face difficulties in deployment due to the cost of massive data annotation and high latency in model iteration. We propose a dynamic interactive learning…
Continual learning for segmentation has recently seen increasing interest. However, all previous works focus on narrow semantic segmentation and disregard panoptic segmentation, an important task with real-world impacts. %a In this paper,…
Endoscopic depth estimation is a critical technology for improving the safety and precision of minimally invasive surgery. It has attracted considerable attention from researchers in medical imaging, computer vision, and robotics. Over the…
This paper presents a fully unsupervised deep change detection approach for mobile robots with 3D LiDAR. In unstructured environments, it is infeasible to define a closed set of semantic classes. Instead, semantic segmentation is…
Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, existing CSS methods…
Visual navigation for cross-embodiment robots is challenging due to variations in robot and camera configurations, which can lead to the failure of navigation tasks. Previous approaches typically rely on collecting massive datasets across…
Autonomous collision-free navigation in cluttered environments requires safe decision-making under partial observability with both static structure and dynamic obstacles. We present \textbf{PanoDP}, a communication-free learning framework…
Self-supervised monocular depth estimation is of significant importance with applications spanning across autonomous driving and robotics. However, the reliance on self-supervision introduces a strong static-scene assumption, thereby posing…
Visual odometry is a fundamental task for many applications on mobile devices and robotic platforms. Since such applications are oftentimes not limited to predefined target domains and learning-based vision systems are known to generalize…
Monocular depth estimation (MDE) has widely applicable but remains highly challenging due to the inherently ill-posed nature of reconstructing 3D scenes from single 2D images. Modern Vision Foundation Models (VFMs), pre-trained on…
We consider the joint design and control of discrete-time stochastic dynamical systems over a finite time horizon. We formulate the problem as a multi-step optimization problem under uncertainty seeking to identify a system design and a…
Depth estimation and 3D object detection are critical for scene understanding but remain challenging to perform with a single image due to the loss of 3D information during image capture. Recent models using deep neural networks have…
Addressing Lidar Panoptic Segmentation (LPS ) is crucial for safe deployment of autonomous vehicles. LPS aims to recognize and segment lidar points w.r.t. a pre-defined vocabulary of semantic classes, including thing classes of countable…
We propose Panoptic Lifting, a novel approach for learning panoptic 3D volumetric representations from images of in-the-wild scenes. Once trained, our model can render color images together with 3D-consistent panoptic segmentation from…
Continual learning (CL) breaks off the one-way training manner and enables a model to adapt to new data, semantics and tasks continuously. However, current CL methods mainly focus on single tasks. Besides, CL models are plagued by…
Real-world robots must operate under evolving dynamics caused by changing operating conditions, external disturbances, and unmodeled effects. These may appear as gradual drifts, transient fluctuations, or abrupt shifts, demanding real-time…
We propose a self-supervised monocular depth estimation network tailored for endoscopic scenes, aiming to infer depth within the gastrointestinal tract from monocular images. Existing methods, though accurate, typically assume consistent…
Understanding the geometric and semantic properties of the scene is crucial in autonomous navigation and particularly challenging in the case of Unmanned Aerial Vehicle (UAV) navigation. Such information may be by obtained by estimating…
Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks…