Search Results for author:
Found 28 papers, 11 papers with code
BRAVE: Broadening the visual encoding of vision-language models
Our results highlight the potential of incorporating different visual biases for a more broad and contextualized visual understanding of VLMs.
Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces
Touch and vision go hand in hand, mutually enhancing our ability to understand the world.
InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes
We introduce InseRF, a novel method for generative object insertion in the NeRF reconstructions of 3D scenes.
Text-Conditioned Resampler For Long Form Video Understanding
In this paper we present a text-conditioned video resampler (TCR) module that uses a pre-trained and frozen visual encoder and large language model (LLM) to process long video sequences for a task.
Ranked #5 on
Video Question Answering
on NExT-QA
LIME: Localized Image Editing via Attention Regularization in Diffusion Models
Diffusion models (DMs) have gained prominence due to their ability to generate high-quality, varied images, with recent advancements in text-to-image generation.
TouchSDF: A DeepSDF Approach for 3D Shape Reconstruction using Vision-Based Tactile Sensing
To address these challenges, we propose TouchSDF, a Deep Learning approach for tactile 3D shape reconstruction that leverages the rich information provided by a vision-based tactile sensor and the expressivity of the implicit neural representation DeepSDF.
TextMesh: Generation of Realistic 3D Meshes From Text Prompts
In addition, we propose a novel way to finetune the mesh texture, removing the effect of high saturation and improving the details of the output 3D mesh.
NeRF-Supervised Deep Stereo
We introduce a novel framework for training deep stereo networks effortlessly and without any ground-truth.
NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions
Pose-conditioned convolutional generative models struggle with high-quality 3D-consistent image generation from single-view datasets, due to their lack of sufficient 3D priors.
Learning Good Features to Transfer Across Tasks and Domains
Besides, we propose a set of strategies to constrain the learned feature spaces, to ease learning and increase the generalization capability of the mapping network, thereby considerably improving the final performance of our framework.
LatentSwap3D: Semantic Edits on 3D Image GANs
3D GANs have the ability to generate latent codes for entire 3D volumes rather than only 2D images.
ParGAN: Learning Real Parametrizable Transformations
Current methods for image-to-image translation produce compelling results, however, the applied transformation is difficult to control, since existing mechanisms are often limited and non-intuitive.
LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction
Most modern deep learning-based multi-view 3D reconstruction techniques use RNNs or fusion modules to combine information from multiple images after independently encoding them.
Unsupervised Novel View Synthesis from a Single Image
Novel view synthesis from a single image aims at generating novel views from a single input image of an object.
Batch Normalization Embeddings for Deep Domain Generalization
Several recent methods use multiple datasets to train models to extract domain-invariant features, hoping to generalize to unseen domains.
Ranked #63 on
Domain Generalization
on PACS
A Divide et Impera Approach for 3D Shape Reconstruction from Multiple Views
Estimating the 3D shape of an object from a single or multiple images has gained popularity thanks to the recent breakthroughs powered by deep learning.
Continual Adaptation for Deep Stereo
Thus, our network architecture and adaptation algorithms realize the first real-time self-adaptive deep stereo system and pave the way for a new paradigm that can facilitate practical deployment of end-to-end architectures for dense disparity regression.
Unsupervised Domain Adaptation for Depth Prediction from Images
Extensive experimental results based on standard datasets and evaluation protocols prove that our technique can address effectively the domain shift issue with both stereo and monocular depth prediction architectures and outperforms other state-of-the-art unsupervised loss functions that may be alternatively deployed to pursue domain adaptation.
Semi-Automatic Labeling for Deep Learning in Robotics
In this paper, we propose Augmented Reality Semi-automatic labeling (ARS), a semi-automatic method which leverages on moving a 2D camera by means of a robot, proving precise camera tracking, and an augmented reality pen to define initial object bounding box, to create large labeled datasets with minimal human intervention.
Real-Time Highly Accurate Dense Depth on a Power Budget using an FPGA-CPU Hybrid SoC
Obtaining highly accurate depth from stereo images in real time has many applications across computer vision and robotics, but in some contexts, upper bounds on power consumption constrain the feasible hardware to embedded platforms such as FPGAs.
Learning Across Tasks and Domains
Recent works have proven that many relevant visual tasks are closely related one to another.
Learning to Adapt for Stereo
Real world applications of stereo depth estimation require models that are robust to dynamic variations in the environment.
Domain invariant hierarchical embedding for grocery products recognition
Moreover, there exist a significant domain shift between the images that should be recognized at test time, taken in stores by cheap cameras, and those available for training, usually just one or a few studio-quality images per product.
Exploiting Semantics in Adversarial Training for Image-Level Domain Adaptation
To prove the effectiveness of our proposal, we show how a semantic segmentation CNN trained on images from the synthetic GTA dataset adapted by our method can improve performance by more than 16% mIoU with respect to the same model trained on synthetic images.
Real-time self-adaptive deep stereo
Deep convolutional neural networks trained end-to-end are the state-of-the-art methods to regress dense disparity maps from stereo pairs.
A deep learning pipeline for product recognition on store shelves
Then, available product databases usually include just one or a few studio-quality images per product (referred to herein as reference images), whilst at test time recognition is performed on pictures displaying a portion of a shelf containing several products and taken in the store by cheap cameras (referred to as query images).
Unsupervised Adaptation for Deep Stereo
Recent ground-breaking works have shown that deep neural networks can be trained end-to-end to regress dense disparity maps directly from image pairs.
Product recognition in store shelves as a sub-graph isomorphism problem
The arrangement of products in store shelves is carefully planned to maximize sales and keep customers happy.
