38 accepted papers
Graph Neural Networks (GNNs) excel at learning from pairwise interactions but often overlook multi-way and hierarchical relationships. Topological Deep Learning (TDL) addresses this limitation by leveraging combinatorial topological spaces, such as simplicial or cell complexes. However, existing TDL…
Sheaf Neural Networks (SNNs) are a powerful algebraic-topology generalization of Graph Neural Networks (GNNs), and have been shown to significantly improve our ability to model complex relational data. While the GNN literature proved that incorporating directionality can substantially boost performa…
We present billboard Splatting (BBSplat) - a novel approach for novel view synthesis based on textured geometric primitives. BBSplat represents the scene as a set of optimizable textured planar primitives with learnable RGB textures and alpha-maps to control their shape. BBSplat primitives can be us…
We present a self-supervised method to improve an agent's abilities in describing arbitrary objects while actively exploring a generic environment. This is a challenging problem, as current models struggle to obtain coherent image captions due to different camera viewpoints and clutter. We propose a…
Achieving dexterous robotic grasping with multi-fingered hands remains a significant challenge. While existing methods rely on complete 3D scans to predict grasp poses, these approaches face limitations due to the difficulty of acquiring high-quality 3D data in real-world scenarios. In this paper, w
Shape completion networks have been used recently in real-world robotic experiments to complete the missing/hidden information in environments where objects are only observed in one or few instances where self-occlusions are bound to occur. Nowadays, most approaches rely on deep neural networks that
Progress in Embodied AI has made it possible for end-to-end-trained agents to navigate in photo-realistic environments with high-level reasoning and zero-shot or language-conditioned behavior, but evaluations and benchmarks are still dominated by simulation. In this work, we focus on the fine-graine…
The task of reassembly is a significant challenge across multiple domains, including archaeology, genomics, and molecular docking, requiring the precise placement and orientation of elements to reconstruct an original structure. In this work, we address key limitations in state-of-the-art Deep Learn…
"We propose to estimate the camera pose of a target RGB image given a 3D Gaussian Splatting (3DGS) model representing the scene. avoids the iterative process typical of analysis-by-synthesis methods (iNeRF) that also require an initialization of the camera pose in order to converge. Instead, our met…
Reassembly tasks play a fundamental role in many fields and multiple approaches exist to solve specific reassembly problems. In this context we posit that a general unified model can effectively address them all irrespective of the input data type (image 3D etc.). We introduce DiffAssemble a Graph N…
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. IFFNeRF is specifically designed to operate in real-time and eliminates the need for an initial pose guess that is proximate to the sought solut…
"When an object detector is deployed in a novel setting it often experiences a drop in performance. This paper studies how an embodied agent can automatically fine-tune a pre-existing object detector while exploring and acquiring images in a new environment without relying on human intervention, i.e…
Vision-and-Language Navigation in Continuous Environments (VLN-CE) is one of the most intuitive yet challenging embodied AI tasks. Agents are tasked to navigate towards a target goal by executing a set of low-level actions, following a series of natural language instructions. All VLN-CE methods in t
This paper proposes the RePAIR dataset that represents a challenging benchmark to test modern computational and data driven methods for puzzle-solving and reassembly tasks. Our dataset has unique properties that are uncommon to current benchmarks for 2D and 3D puzzle solving. The fragments and fract…
"Unsupervised 3D keypoints estimation from Point Cloud Data (PCD) is a complex task, even more challenging when an object shape is deforming. As keypoints should be semantically and geometrically consistent across all the 3D frames – each keypoint should be anchored to a specific part of the deformi…
This letter presents XBG (eXteroceptive Behaviour Generation), a multimodal end-to-end Imitation Learning (IL) system for whole-body autonomous humanoid robots used in real-world Human-Robot Interaction (HRI) scenarios. The main contribution is an architecture for learning HRI behaviours using a dat
Real-world robotic grasping can be done robustly if a complete 3D Point Cloud Data (PCD) of an object is available. 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 gras…
We tackle audio-visual inpainting, the problem of completing an image in such a way to be consistent with the sound associated to the scene. To this end, we propose a multimodal, audio-visual inpainting method (AVIN), and show how to leverage sound to reconstruct semantically consistent images. AVIN…
Standard Unsupervised Domain Adaptation (UDA) methods assume the availability of both source and target data during the adaptation. In this work, we investigate Source-free Unsupervised Domain Adaptation (SF-UDA), a specific case of UDA where a model is adapted to a target domain without access to s…
Wide-scale use of visual surveillance in public spaces puts individual privacy at stake while increasing resource consumption (energy, bandwidth, and computation). Neuromorphic vision sensors (event-cameras) have been recently considered a valid solution to the privacy issue because they do not capt…
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. Our proposed model adheres to the following principles: i) keypoints inference is fully unsupervised (no annotatio…
We study the problem of learning association between face and voice. Prior works adopt pairwise or triplet loss formulations to learn an embedding space amenable for associated matching and verification tasks. Albeit showing some progress, such loss formulations are restrictive due to dependency on…
"The estimation of the camera poses associated with a set of images commonly relies on feature matches between the images. In contrast, we are the first to address this challenge by using objectness regions to guide the pose estimation problem rather than explicit semantic object detections. We prop…
We solve object localisation in partial scenes, a new problem of estimating the unknown position of an object (e.g. where is the bag?) given a partial 3D scan of a scene. The proposed solution is based on a novel scene graph model, the Spatial Commonsense Graph (SCG), where objects are the nodes and…
In this paper, we tackle data-driven 3D point cloud registration. Given point correspondences, the standard Kabsch algorithm provides an optimal rotation estimate. This allows to train registration models in an end-to-end manner by differentiating the SVD operation. However, given the initial rotati…
Acoustic images constitute an emergent data modality for multimodal scene understanding. Such images have the peculiarity to distinguish the spectral signature of sounds coming from different directions in space, thus providing richer information than the one derived from mono and binaural microphon…
In this paper, we focus on the problem of learning online an optimal policy for Active Visual Search (AVS) of objects in unknown indoor environments. We propose POMP++, a planning strategy that introduces a novel formulation on top of the classic Partially Observable Monte Carlo Planning (POMCP) fra…
In this work we address the problem of autonomous 3D exploration of an unknown indoor environment using a depth camera. We cast the problem as the estimation of the Next Best View (NBV) that maximises the coverage of the unknown area. We do this by re-formulating NBV estimation as a classification p…
We propose a novel information gain metric that combines hand-crafted and data-driven metrics to address the next best view problem for autonomous 3-D mapping of unknown indoor environments. For the hand-crafted metric, we propose an entropy-based information gain that accounts for the previous view
Recent approaches on trajectory forecasting use tracklets to predict the future positions of pedestrians exploiting Long Short Term Memory (LSTM) architectures. This paper shows that adding vislets, that is, short sequences of head pose estimations, allows to increase significantly the trajectory fo…
Though a long-studied problem, motion segmentation has yet to migrate into practical applications. We argue that a vital step towards that goal lies in addressing motion segmentation for the specific setting of interest. To this end, this paper presents a new approach for image-based motion segmenta…
Room reconstruction from sound is the problem of estimating indoor space boundaries given only a set of sound events acquired by an array of microphones. In order to find a solution in realistic scenarios, it is necessary a robust and practical method that can solve the echo labelling problem, i.e.…
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. By embedding the projective depths into the projective parameters of the points and views, we d…
In this paper we deal with the problem of recovering affine camera calibration and objects position/occupancy from multi-view images using the information from image detections. We show that remarkable object localisation and volumetric occupancy can be recovered by including both geometrical constr…
Estimation of Time Difference of Arrivals (TDOAs) corresponding to early room reflections can be formulated as a Blind Channel Identification (BCI) problem, exploiting signals acquired by a set of microphones, given an unknown transmitted source. To cope with the intrinsic noise sensitivity and ill-…
A fundamental step to solve bin-picking and grasping problems is the accurate estimation of an object 3D pose. Such visual task usually rely on profusely textured objects: standard procedures such as detection of interest points or computation of appearance-based descriptors are favoured by using a
This paper shows for the first time that is possible to reconstruct the position of rigid objects and to jointly recover affine camera calibration solely from a set of object detections in a video sequence. In practice, this work can be considered as the extension of Tomasi and Kanade factorization…
The fact that image data samples lie on a manifold has been successfully exploited in many learning and inference problems. In this paper we leverage the specific structure of data in order to improve recognition accuracies in general recognition tasks. In particular we propose a novel framework tha…