Related papers: Image-Conditioned Adaptive Parameter Tuning for Vi…
A strength of parameterized algorithmics is that each problem can be parameterized by an essentially inexhaustible set of parameters. Usually, the choice of the considered parameter is informed by the theoretical relations between…
We consider how to most efficiently leverage teleoperator time to collect data for learning robust image-based value functions and policies for sparse reward robotic tasks. To accomplish this goal, we modify the process of data collection…
Curriculum Learning (CL), drawing inspiration from natural learning patterns observed in humans and animals, employs a systematic approach of gradually introducing increasingly complex training data during model development. Our work…
Traditional monocular direct visual odometry (DVO) is one of the most famous methods to estimate the ego-motion of robots and map environments from images simultaneously. However, DVO heavily relies on high-quality images and accurate…
Visual tracking is a fundamental problem in computer vision. Recently, some deep-learning-based tracking algorithms have been achieving record-breaking performances. However, due to the high complexity of deep learning, most deep trackers…
Traditional preference tuning methods for LLMs/Visual Generative Models often rely solely on reward model labeling, which can be opaque, offer limited insights into the rationale behind preferences, and are prone to issues such as reward…
Visual token pruning methods effectively mitigate the quadratic computational growth caused by processing high-resolution images and video frames in vision-language models (VLMs). However, existing approaches rely on predefined pruning…
Integration of Visual Inertial Odometry (VIO) methods into a modular control system designed for deployment of Unmanned Aerial Vehicles (UAVs) and teams of cooperating UAVs in real-world conditions are presented in this paper. Reliability…
While pre-trained visual representations have significantly advanced imitation learning, they are often task-agnostic as they remain frozen during policy learning. In this work, we explore leveraging pre-trained text-to-image diffusion…
We present HyperMorph, a learning-based strategy for deformable image registration that removes the need to tune important registration hyperparameters during training. Classical registration methods solve an optimization problem to find a…
This paper proposes two new algorithms for certified perception in safety-critical robotic applications. The first is a Certified Visual Odometry algorithm, which uses a RGBD camera with bounded sensor noise to construct a visual odometry…
Visual-inertial-odometry has attracted extensive attention in the field of autonomous driving and robotics. The size of Field of View (FoV) plays an important role in Visual-Odometry (VO) and Visual-Inertial-Odometry (VIO), as a large FoV…
We propose XVO, a semi-supervised learning method for training generalized monocular Visual Odometry (VO) models with robust off-the-self operation across diverse datasets and settings. In contrast to standard monocular VO approaches which…
A key task in embedded vision is visual odometry (VO), which estimates camera motion from visual sensors, and it is a core component in many embedded power-constrained systems, from autonomous robots to augmented and virtual reality…
We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of…
Existing pedestrian attribute recognition (PAR) algorithms are mainly developed based on a static image, however, the performance is unreliable in challenging scenarios, such as heavy occlusion, motion blur, etc. In this work, we propose to…
Visual odometry estimates the motion of a moving camera based on visual input. Existing methods, mostly focusing on two-view point tracking, often ignore the rich temporal context in the image sequence, thereby overlooking the global motion…
Due to increasing interest in adapting models on resource-constrained edges, parameter-efficient transfer learning has been widely explored. Among various methods, Visual Prompt Tuning (VPT), prepending learnable prompts to input space,…
Visual Prompt Tuning (VPT) has proven effective for parameter-efficient adaptation of pre-trained vision models to downstream tasks by inserting task-specific learnable prompt tokens. Despite its empirical success, a comprehensive…
Deep learning-based Visual SLAM (vSLAM) systems exhibit exceptional geometric reasoning capabilities, yet their prohibitive computational overhead severely restricts deployment on resource-constrained autonomous platforms. This paper…