Search Results for author:
Found 71 papers, 29 papers with code
Gaussian Heritage: 3D Digitization of Cultural Heritage with Integrated Object Segmentation
We propose a pipeline to generate a 3D replica of a scene using only RGB images (e. g. photos of a museum) and then extract a model for each item of interest (e. g. pieces in the exhibit).
SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapes
Unsupervised 3D keypoints estimation from Point Cloud Data (PCD) is a complex task, even more challenging when an object shape is deforming.
6DGS: 6D Pose Estimation from a Single Image and a 3D Gaussian Splatting Model
Each Ellicell ray is associated with the rendering parameters of each ellipsoid, which in turn is used to obtain the best bindings between the target image pixels and the cast rays.
I2EDL: Interactive Instruction Error Detection and Localization
We evaluate the proposed I2EDL on a dataset of instructions containing errors, and further devise a novel metric, the Success weighted by Interaction Number (SIN), to reflect both the navigation performance and the interaction effectiveness.
Contrastive Gaussian Clustering: Weakly Supervised 3D Scene Segmentation
Recent works in novel-view synthesis have shown how to model the appearance of a scene via a cloud of 3D Gaussians, and how to generate accurate images from a given viewpoint by projecting on it the Gaussians before $\alpha$ blending their color.
Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation
We propose a novel approach for SF-OSDA that exploits the granularity of target-private categories by segregating their samples into multiple unknown classes.
HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior
We demonstrate the effectiveness of our approach on two open datasets: SnapshotPeople and X-Humans.
IFFNeRF: Initialisation Free and Fast 6DoF pose estimation from a single image and a NeRF model
We introduce IFFNeRF to estimate the six degrees-of-freedom (6DoF) camera pose of a given image, building on the Neural Radiance Fields (NeRF) formulation.
Mind the Error! Detection and Localization of Instruction Errors in Vision-and-Language Navigation
Moreover, we formally define the task of Instruction Error Detection and Localization, and establish an evaluation protocol on top of our benchmark dataset.
Towards the Reusability and Compositionality of Causal Representations
Causal Representation Learning (CRL) aims at identifying high-level causal factors and their relationships from high-dimensional observations, e. g., images.
PRAGO: Differentiable Multi-View Pose Optimization From Objectness Detections
Robustly estimating camera poses from a set of images is a fundamental task which remains challenging for differentiable methods, especially in the case of small and sparse camera pose graphs.
DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly
Reassembly tasks play a fundamental role in many fields and multiple approaches exist to solve specific reassembly problems.
mmFUSION: Multimodal Fusion for 3D Objects Detection
The strong multi-modal features from the mmFUSION framework are fed to a simple 3D detection head for 3D predictions.
Learnable Data Augmentation for One-Shot Unsupervised Domain Adaptation
This paper presents a classification framework based on learnable data augmentation to tackle the One-Shot Unsupervised Domain Adaptation (OS-UDA) problem.
Leveraging Next-Active Objects for Context-Aware Anticipation in Egocentric Videos
Compared to existing video modeling architectures for action anticipation, NAOGAT captures the relationship between objects and the global scene context in order to predict detections for the next active object and anticipate relevant future actions given these detections, leveraging the objects' dynamics to improve accuracy.
SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data
This paper proposes a new method to infer keypoints from arbitrary object categories in practical scenarios where point cloud data (PCD) are noisy, down-sampled and arbitrarily rotated.
Person Re-Identification without Identification via Event Anonymization
In this work, we also bring to the community the first ever event-based person ReId dataset gathered to evaluate the performance of our approach.
Guided Attention for Next Active Object @ EGO4D STA Challenge
In this technical report, we describe the Guided-Attention mechanism based solution for the short-term anticipation (STA) challenge for the EGO4D challenge.
Ranked #3 on
Short-term Object Interaction Anticipation
on Ego4D
Enhancing Next Active Object-based Egocentric Action Anticipation with Guided Attention
To this end, we propose a novel approach that applies a guided attention mechanism between the objects, and the spatiotemporal features extracted from video clips, enhancing the motion and contextual information, and further decoding the object-centric and motion-centric information to address the problem of STA in egocentric videos.
Target-driven One-Shot Unsupervised Domain Adaptation
Unlike existing methods, our augmentation module allows for strong transformations of the source samples, and the style of the single target sample available is exploited to guide the augmentation by ensuring perceptual similarity.
One-shot Unsupervised Domain Adaptation
Unsupervised Domain Adaptation
3DoF Localization from a Single Image and an Object Map: the Flatlandia Problem and Dataset
Efficient visual localization is crucial to many applications, such as large-scale deployment of autonomous agents and augmented reality.
Positional Diffusion: Ordering Unordered Sets with Diffusion Probabilistic Models
We present Positional Diffusion, a plug-and-play graph formulation with Diffusion Probabilistic Models to address positional reasoning.
Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation
We propose a novel approach for the SF-UDA setting based on a loss reweighting strategy that brings robustness against the noise that inevitably affects the pseudo-labels.
Self-improving object detection via disagreement reconciliation
Object detectors often experience a drop in performance when new environmental conditions are insufficiently represented in the training data.
Anticipating Next Active Objects for Egocentric Videos
This paper addresses the problem of anticipating the next-active-object location in the future, for a given egocentric video clip where the contact might happen, before any action takes place.
Look Around and Learn: Self-Training Object Detection by Exploration
When an object detector is deployed in a novel setting it often experiences a drop in performance.
3DSGrasp: 3D Shape-Completion for Robotic Grasp
However, in practice, PCDs are often incomplete when objects are viewed from few and sparse viewpoints before the grasping action, leading to the generation of wrong or inaccurate grasp poses.
Leveraging commonsense for object localisation in partial scenes
With the proposed graph-based scene representation, we estimate the unknown position of the target object using a Graph Neural Network that implements a novel attentional message passing mechanism.
VM-NeRF: Tackling Sparsity in NeRF with View Morphing
A well-known limitation of NeRF methods is their reliance on data: the fewer the viewpoints, the higher the likelihood of overfitting.
Geolocation of Cultural Heritage using Multi-View Knowledge Graph Embedding
Knowledge Graphs (KGs) have proven to be a reliable way of structuring data.
Learning Branched Fusion and Orthogonal Projection for Face-Voice Association
In addition, we leverage cross-modal verification and matching tasks to analyze the impact of multiple languages on face-voice association.
Co-Located Human-Human Interaction Analysis using Nonverbal Cues: A Survey
Automated co-located human-human interaction analysis has been addressed by the use of nonverbal communication as measurable evidence of social and psychological phenomena.
PoserNet: Refining Relative Camera Poses Exploiting Object Detections
The estimation of the camera poses associated with a set of images commonly relies on feature matches between the images.
GANzzle: Reframing jigsaw puzzle solving as a retrieval task using a generative mental image
Puzzle solving is a combinatorial challenge due to the difficulty of matching adjacent pieces.
Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance
This paper presents a novel end-to-end method for the problem of skeleton-based unsupervised human action recognition.
Spatial Commonsense Graph for Object Localisation in Partial Scenes
The SCG is used to estimate the unknown position of the target object in two steps: first, we feed the SCG into a novel Proximity Prediction Network, a graph neural network that uses attention to perform distance prediction between the node representing the target object and the nodes representing the observed objects in the SCG; second, we propose a Localisation Module based on circular intersection to estimate the object position using all the predicted pairwise distances in order to be independent of any reference system.
Semantically Grounded Visual Embeddings for Zero-Shot Learning
Zero-shot learning methods rely on fixed visual and semantic embeddings, extracted from independent vision and language models, both pre-trained for other large-scale tasks.
Fusion and Orthogonal Projection for Improved Face-Voice Association
Prior works adopt pairwise or triplet loss formulations to learn an embedding space amenable for associated matching and verification tasks.
POINTVIEW-GCN: 3D SHAPE CLASSIFICATION WITH MULTI-VIEW POINT CLOUDS
We address 3D shape classification with partial point cloud inputs captured from multiple viewpoints around the object.
Ranked #1 on
3D Point Cloud Classification
on ModelNet40
(Just) A Spoonful of Refinements Helps the Registration Error Go Down
However, given the initial rotation estimate supplied by Kabsch, we show we can improve point correspondence learning during model training by extending the original optimization problem.
Lifting Monocular Events to 3D Human Poses
Here we propose the first learning-based method for 3D human pose from a single stream of events.
Ranked #2 on
3D Human Pose Estimation
on DHP19
Consistent Mesh Colors for Multi-View Reconstructed 3D Scenes
We then use this color in a re-weighting ratio for the best-view texture, which is identified by prior mesh texturing work, to create a spatial consistent texture map.
LIGHTS: LIGHT Specularity Dataset for specular detection in Multi-view
Therefore, we propose a novel physically-based rendered LIGHT Specularity (LIGHTS) Dataset for the evaluation of the specular highlight detection task.
AIforCOVID: predicting the clinical outcomes in patients with COVID-19 applying AI to chest-X-rays. An Italian multicentre study
Exhaustive evaluation shows promising performance both in 10-fold and leave-one-centre-out cross-validation, implying that clinical data and images have the potential to provide useful information for the management of patients and hospital resources.
Where to Explore Next? ExHistCNN for History-aware Autonomous 3D Exploration
In this work we address the problem of autonomous 3D exploration of an unknown indoor environment using a depth camera.
Single Image Human Proxemics Estimation for Visual Social Distancing
In this work, we address the problem of estimating the so-called "Social Distancing" given a single uncalibrated image in unconstrained scenarios.
A Versatile Crack Inspection Portable System based on Classifier Ensemble and Controlled Illumination
This paper presents a novel setup for automatic visual inspection of cracks in ceramic tile as well as studies the effect of various classifiers and height-varying illumination conditions for this task.
POMP: Pomcp-based Online Motion Planning for active visual search in indoor environments
Our POMP method uses as input the current pose of an agent (e. g. a robot) and a RGB-D frame.
Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning
This paper tackles the problem of human action recognition, defined as classifying which action is displayed in a trimmed sequence, from skeletal data.
Ranked #1 on
Skeleton Based Action Recognition
on MSR ActionPairs
The Visual Social Distancing Problem
One of the main and most effective measures to contain the recent viral outbreak is the maintenance of the so-called Social Distancing (SD).
Cross-modal Speaker Verification and Recognition: A Multilingual Perspective
Recent years have seen a surge in finding association between faces and voices within a cross-modal biometric application along with speaker recognition.
Complex-Object Visual Inspection via Multiple Lighting Configurations
The design of an automatic visual inspection system is usually performed in two stages.
An integrated light management system with real-time light measurement and human perception
Illumination is important for well-being, productivity and safety across several environments, including offices, retail shops and industrial warehouses.
Weakly Supervised Geodesic Segmentation of Egyptian Mummy CT Scans
We aim at digitally unwrapping the mummy and identify different segments such as body, bandages and jewelry.
re-OBJ: Jointly Learning the Foreground and Background for Object Instance Re-identification
Conventional approaches to object instance re-identification rely on matching appearances of the target objects among a set of frames.
CvxPnPL: A Unified Convex Solution to the Absolute Pose Estimation Problem from Point and Line Correspondences
We present a new convex method to estimate 3D pose from mixed combinations of 2D-3D point and line correspondences, the Perspective-n-Points-and-Lines problem (PnPL).
Human-centric light sensing and estimation from RGBD images: The invisible light switch
ILS may therefore dim those luminaires, which are not seen by the user, resulting in an effective energy saving, especially in large open offices (where light may otherwise be ON everywhere for a single person).
Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Vislets
In this work, we explore the correlation between people trajectories and their head orientations.
RGBD2lux: Dense light intensity estimation with an RGBD sensor
The proposed method uses both depth data and images from the sensor to provide a dense measure of light intensity in the field of view of the camera.
Visual Graphs from Motion (VGfM): Scene understanding with object geometry reasoning
Recent approaches on visual scene understanding attempt to build a scene graph -- a computational representation of objects and their pairwise relationships.
MX-LSTM: mixing tracklets and vislets to jointly forecast trajectories and head poses
Recent approaches on trajectory forecasting use tracklets to predict the future positions of pedestrians exploiting Long Short Term Memory (LSTM) architectures.
Objects Localisation from Motion with Constraints
This problem is modelled as the estimation of a set of quadrics given 2D conics fit to the object bounding boxes.
“Seeing is Believing”: Pedestrian Trajectory Forecasting Using Visual Frustum of Attention
In this paper we show the importance of the head pose estimation in the task of trajectory forecasting.
A Benchmark and Evaluation of Non-Rigid Structure from Motion
To validate the applicability of this data set, and provide an investigation into the state of the art of NRSfM, including potential directions forward, we here present a benchmark and a scrupulous evaluation using this data set.
Practical Projective Structure From Motion (P2SfM)
This paper presents a solution to the Projective Structure from Motion (PSfM) problem able to deal efficiently with missing data, outliers and, for the first time, large scale 3D reconstruction scenarios.
Probabilistic Structure From Motion With Objects (PSfMO)
We show that remarkable object localisation and volumetric occupancy can be recovered by including both geometrical constraints and prior information given by objects CAD models from the ShapeNet dataset.
Manifold Constrained Low-Rank Decomposition
Low-rank decomposition (LRD) is a state-of-the-art method for visual data reconstruction and modelling.
Structure From Motion With Objects
In practice, this work can be considered as the extension of Tomasi and Kanade factorization method using objects.
Sparse Representation Classification With Manifold Constraints Transfer
The fact that image data samples lie on a manifold has been successfully exploited in many learning and inference problems.
PiMPeR: Piecewise Dense 3D Reconstruction from Multi-View and Multi-Illumination Images
Unlike multi-view stereo and multi-view photometric stereo methods, this pipeline deals with wide-baseline images that are uncalibrated, in terms of both camera parameters and lighting conditions.
3D Pose from Detections
We present a novel method to infer, in closed-form, a general 3D spatial occupancy and orientation of a collection of rigid objects given 2D image detections from a sequence of images.
