3 citations · 4 across the 8 of their papers we have counts for
9 papers
SplatFill: 3D Scene Inpainting via Depth-Guided Gaussian Splatting
Mahtab Dahaghin, Milind G. Padalkar, Matteo Toso +1
3D Gaussian Splatting (3DGS) has enabled the creation of highly realistic 3D scene representations from sets of multi-view images. However, inpainting missing regions, whether due…
AccioScene: Compositional 3D Scene Generation via Graph Diffusion and Interaction-driven Critics
Yao Wei, Matteo Toso, Pietro Morerio +3
This paper presents a framework for generating 3D indoor scenes from text prompts. Existing methods often formulate scene synthesis as an object layout prediction problem condition…
Maps from Motion (MfM): Generating 2D Semantic Maps from Sparse Multi-view Images
Matteo Toso, Stefano Fiorini, Stuart James +1
World-wide detailed 2D maps require enormous collective efforts. OpenStreetMap is the result of 11 million registered users manually annotating the GPS location of over 1.75 billio…
Gaussian Heritage: 3D Digitization of Cultural Heritage with Integrated Object Segmentation
Mahtab Dahaghin, Myrna Castillo, Kourosh Riahidehkordi +2
The creation of digital replicas of physical objects has valuable applications for the preservation and dissemination of tangible cultural heritage. However, existing methods are o…
Contrastive Gaussian Clustering: Weakly Supervised 3D Scene Segmentation
Myrna C. Silva, Mahtab Dahaghin, Matteo Toso +1
We introduce Contrastive Gaussian Clustering, a novel approach capable of provide segmentation masks from any viewpoint and of enabling 3D segmentation of the scene. Recent works i…
PRAGO: Differentiable Multi-View Pose Optimization From Objectness Detections
Matteo Taiana, Matteo Toso, Stuart James +1
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…
3DoF Localization from a Single Image and an Object Map: the Flatlandia Problem and Dataset
Matteo Toso, Matteo Taiana, Stuart James +1
Efficient visual localization is crucial to many applications, such as large-scale deployment of autonomous agents and augmented reality. Traditional visual localization, while ach…
PoserNet: Refining Relative Camera Poses Exploiting Object Detections
Matteo Taiana, Matteo Toso, Stuart James +1
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…
Rethinking Pose in 3D: Multi-stage Refinement and Recovery for Markerless Motion Capture
Denis Tome, Matteo Toso, Lourdes Agapito +1
We propose a CNN-based approach for multi-camera markerless motion capture of the human body. Unlike existing methods that first perform pose estimation on individual cameras and g…