Marco Cannici
YOU?
Author Swipe
View article: LiDAR Registration with Visual Foundation Models
LiDAR Registration with Visual Foundation Models Open
View article: Perturbed State Space Feature Encoders for Optical Flow with Event Cameras
Perturbed State Space Feature Encoders for Optical Flow with Event Cameras Open
With their motion-responsive nature, event-based cameras offer significant advantages over traditional cameras for optical flow estimation. While deep learning has improved upon traditional methods, current neural networks adopted for even…
View article: LiDAR Registration with Visual Foundation Models
LiDAR Registration with Visual Foundation Models Open
LiDAR registration is a fundamental task in robotic mapping and localization. A critical component of aligning two point clouds is identifying robust point correspondences using point descriptors. This step becomes particularly challenging…
View article: GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control Open
We present GEM, a Generalizable Ego-vision Multimodal world model that predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories. Hence, our model has precise control over object dynamics, ego-agent…
View article: Monocular Event-Based Vision for Obstacle Avoidance with a Quadrotor
Monocular Event-Based Vision for Obstacle Avoidance with a Quadrotor Open
We present the first static-obstacle avoidance method for quadrotors using just an onboard, monocular event camera. Quadrotors are capable of fast and agile flight in cluttered environments when piloted manually, but vision-based autonomou…
View article: FaVoR: Features via Voxel Rendering for Camera Relocalization
FaVoR: Features via Voxel Rendering for Camera Relocalization Open
Camera relocalization methods range from dense image alignment to direct camera pose regression from a query image. Among these, sparse feature matching stands out as an efficient, versatile, and generally lightweight approach with numerou…
View article: Mitigating Motion Blur in Neural Radiance Fields with Events and Frames
Mitigating Motion Blur in Neural Radiance Fields with Events and Frames Open
Neural Radiance Fields (NeRFs) have shown great potential in novel view synthesis. However, they struggle to render sharp images when the data used for training is affected by motion blur. On the other hand, event cameras excel in dynamic …
View article: Revisiting Token Pruning for Object Detection and Instance Segmentation
Revisiting Token Pruning for Object Detection and Instance Segmentation Open
Vision Transformers (ViTs) have shown impressive performance in computer vision, but their high computational cost, quadratic in the number of tokens, limits their adoption in computation-constrained applications. However, this large numbe…
View article: Low-power event-based face detection with asynchronous neuromorphic hardware
Low-power event-based face detection with asynchronous neuromorphic hardware Open
The rise of mobility, IoT and wearables has shifted processing to the edge of the sensors, driven by the need to reduce latency, communication costs and overall energy consumption. While deep learning models have achieved remarkable result…
View article: A 5-Point Minimal Solver for Event Camera Relative Motion Estimation
A 5-Point Minimal Solver for Event Camera Relative Motion Estimation Open
Event-based cameras are ideal for line-based motion estimation, since they predominantly respond to edges in the scene. However, accurately determining the camera displacement based on events continues to be an open problem. This is becaus…
View article: A 5-Point Minimal Solver for Event Camera Relative Motion Estimation
A 5-Point Minimal Solver for Event Camera Relative Motion Estimation Open
Event-based cameras are ideal for line-based motion estimation, since they predominantly respond to edges in the scene. However, accurately determining the camera displacement based on events continues to be an open problem. This is becaus…
View article: Deep Visual Odometry with Events and Frames
Deep Visual Odometry with Events and Frames Open
Visual Odometry (VO) is crucial for autonomous robotic navigation, especially in GPS-denied environments like planetary terrains. To improve robustness, recent model-based VO systems have begun combining standard and event-based cameras. W…
View article: E<sup>2</sup>(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition
E<sup>2</sup>(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition Open
Event cameras are novel bio-inspired sensors, which asynchronously capture pixel-level intensity changes in the form of "events". Due to their sensing mechanism, event cameras have little to no motion blur, a very high temporal resolution …
View article: 6 DoF Pose Regression via Differentiable Rendering
6 DoF Pose Regression via Differentiable Rendering Open
View article: Neural Weighted A*: Learning Graph Costs and Heuristics with Differentiable Anytime A*
Neural Weighted A*: Learning Graph Costs and Heuristics with Differentiable Anytime A* Open
View article: E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition
E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition Open
Event cameras are novel bio-inspired sensors, which asynchronously capture pixel-level intensity changes in the form of "events". Due to their sensing mechanism, event cameras have little to no motion blur, a very high temporal resolution …
View article: DA4Event: Towards Bridging the Sim-to-Real Gap for Event Cameras Using Domain Adaptation
DA4Event: Towards Bridging the Sim-to-Real Gap for Event Cameras Using Domain Adaptation Open
Event cameras are novel bio-inspired sensors, which asynchronously capture pixel-level intensity changes in the form of "events". The innovative way they acquire data presents several advantages over standard devices, especially in poor li…
View article: N-ROD: a Neuromorphic Dataset for Synthetic-to-Real Domain Adaptation
N-ROD: a Neuromorphic Dataset for Synthetic-to-Real Domain Adaptation Open
Event cameras are novel neuromorphic sensors, which asynchronously capture pixel-level intensity changes in the form of "events". Event simulation from existing RGB datasets is commonly used to overcome the need of large amount of annotate…
View article: Skeleton-based action recognition via spatial and temporal transformer networks
Skeleton-based action recognition via spatial and temporal transformer networks Open
View article: DA4Event: towards bridging the Sim-to-Real Gap for Event Cameras using\n Domain Adaptation
DA4Event: towards bridging the Sim-to-Real Gap for Event Cameras using\n Domain Adaptation Open
Event cameras are novel bio-inspired sensors, which asynchronously capture\npixel-level intensity changes in the form of "events". The innovative way they\nacquire data presents several advantages over standard devices, especially in\npoor…
View article: Spatial Temporal Transformer Network for Skeleton-Based Action Recognition
Spatial Temporal Transformer Network for Skeleton-Based Action Recognition Open
View article: Matrix-LSTM: a Differentiable Recurrent Surface for Asynchronous Event-Based Data.
Matrix-LSTM: a Differentiable Recurrent Surface for Asynchronous Event-Based Data. Open
Dynamic Vision Sensors (DVSs) asynchronously stream events in correspondence of pixels subject to brightness changes. Differently from classic vision devices, they produce a sparse representation of the scene. Therefore, to apply standard …
View article: A Differentiable Recurrent Surface for Asynchronous Event-Based Data
A Differentiable Recurrent Surface for Asynchronous Event-Based Data Open
View article: Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras
Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras Open
Event-based cameras, also known as neuromorphic cameras, are bioinspired sensors able to perceive changes in the scene at high frequency with low power consumption. Becoming available only very recently, a limited amount of work addresses …
View article: Attention Mechanisms for Object Recognition With Event-Based Cameras
Attention Mechanisms for Object Recognition With Event-Based Cameras Open
Event-based cameras are neuromorphic sensors capable of efficiently encoding visual information in the form of sparse sequences of events. Being biologically inspired, they are commonly used to exploit some of the computational and power c…
View article: Attention Mechanisms for Object Recognition with Event-Based Cameras
Attention Mechanisms for Object Recognition with Event-Based Cameras Open
Event-based cameras are neuromorphic sensors capable of efficiently encoding visual information in the form of sparse sequences of events. Being biologically inspired, they are commonly used to exploit some of the computational and power c…
View article: Asynchronous Convolutional Networks for Object Detection in Neuromorphic\n Cameras
Asynchronous Convolutional Networks for Object Detection in Neuromorphic\n Cameras Open
Event-based cameras, also known as neuromorphic cameras, are bioinspired\nsensors able to perceive changes in the scene at high frequency with low power\nconsumption. Becoming available only very recently, a limited amount of work\naddress…