Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

Deep learning has revolutionized the field of computer vision, a success largely attributable to the growing size of models, datasets, and computational power. Simultaneously, a critical pain point arises as several computer vision applications are deploye ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

We consider the problem of compressing an information source when a correlated one is available as side information only at the decoder side, which is a special case of the distributed source coding problem in information theory. In particular, we consider ...

To obtain a more complete understanding of material microstructure at the nanoscale and to gain profound insights into their properties, there is a growing need for more efficient and precise methods that can streamline the process of 3D imaging using a tr ...

The Joint Photographic Experts Group (JPEG) AI learning-based image coding system is an ongoing joint standardization effort between International Organization for Standardization (ISO), International Electrotechnical Commission (IEC), and International Te ...

Reading out neuronal activity from three-dimensional (3D) functional imaging requires segmenting and tracking individual neurons. This is challenging in behaving animals if the brain moves and deforms. The traditional approach is to train a convolutional n ...

In the current deep learning paradigm, the amount and quality of training data are as critical as the network architecture and its training details. However, collecting, processing, and annotating real data at scale is difficult, expensive, and time-consum ...

In this paper we propose a Monte Carlo maximum likelihood estimation strategy for discretely observed Wright–Fisher diffusions. Our approach provides an unbiased estimator of the likelihood function and is based on exact simulation techniques that are of s ...

This paper introduces TACOSS a text-image alignment approach that allows explainable land cover semantic segmentation by directly integrating semantic concepts encoded from texts. TACOSS combines convolutional neural networks for visual feature extraction ...

Text-to-image models, such as Stable Diffusion, can generate high-quality images from simple textual prompts. With methods such as Textual Inversion, it is possible to expand the vocabulary of these models with additional concepts, by learning the vocabula ...

Object-centric learning has gained significant attention over the last years as it can serve as a powerful tool to analyze complex scenes as a composition of simpler entities. Well-established tasks in computer vision, such as object detection or instance ...

State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs). Although CNNs offer promising perspectives for 2D image compression, extending such models to omnidirectional images is not straightforward. First, omn ...

Large training datasets have played a vital role in the success of modern deep learning methods in computer vision. But, obtaining sufficient amount of training data is challenging, specially when annotating volumetric images. This is because fully annotat ...

The field of computational topology has developed many powerful tools to describe the shape of data, offering an alternative point of view from classical statistics. This results in a variety of complex structures that are not always directly amenable for ...

While supervised object detection and segmentation methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on. To address this when annotating data is prohibitively e ...

Human visual system relies on both monocular focusness cues and binocular stereo cues to gain effective 3D perception. Correspondingly, depth from focus/defocus (DfF/DfD) and stereo matching are two most studied passive depth sensing schemes, which are tra ...

An innovative photogrammetric pipeline has been developed by INAF-Padova for the processing of the stereo images from the CaSSIS (Colour and Stereo Imaging System) (Thomas et al., 2014). CaSSIS is the multispectral stereo push frame camera on board ExoMars ...

Image classification has significantly improved using deep learning. This is mainly due to convolutional neural networks (CNNs) that are capable of learning rich feature extractors from large datasets. However, most deep learning classification methods are ...

Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching

Chat with Graph Search

Aggregating Spatial and Photometric Context for Photometric Stereo

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Robust machine learning for neuroscientific inference

Neural Distributed Image Compression with Cross-Attention Feature Alignment

3D reconstruction of curvilinear one-dimensional objects viewed in transmission electron microscopy

The JPEG AI Standard: Providing Efficient Human and Machine Visual Data Consumption

Automated neuron tracking inside moving and deforming C. elegans using deep learning and targeted augmentation

AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration

Unbiased Likelihood Estimation of Wright–Fisher Diffusion Processes

Text as a Richer Source of Supervision in Semantic Segmentation Tasks

VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text

Unsupervised Visual Entity Abstraction towards 2D and 3D Compositional Models

OSLO: On-the-Sphere Learning for Omnidirectional Images and Its Application to 360-Degree Image Compression

Object Priors for Volumetric Image Segmentation

Reduced representations of complexes, signals, and multifiltrations

Self-supervised Segmentation via Background Inpainting

Deep eyes: Joint depth inference using monocular and binocular cues

3DPD: A photogrammetric pipeline for a PUSH frame stereo cameras

Fidelity Estimation Improves Noisy-Image Classification with Pretrained Networks