Hamid Laga

• PhD
• Senior Researcher at University of South Australia

Quantum neural networks have emerged as a promising approach to solving complex problems across various domains, especially when integrated with classical methods. Several hybrid quantum-classical architectures have been developed to leverage the potential of quantum advantages for image classification tasks. The design of the quantum layer plays a...

Semantic instance completion aims to recover the complete 3D shapes of foreground objects together with their labels from a partial 2.5D scan of a scene. Previous works have relied on full supervision, which requires ground-truth annotations, in the form of bounding boxes and complete 3D objects. This has greatly limited their real-world applicatio...

Neural fields such as DeepSDF and Neural Radiance Fields have recently revolutionized novel-view synthesis and 3D reconstruction from RGB images and videos. However, achieving high-quality representation, reconstruction, and rendering requires deep neural networks, which are slow to train and evaluate. Although several acceleration techniques have...

We propose a novel framework for the statistical analysis of genus-zero 4D surfaces, i.e., 3D surfaces that deform and evolve over time. This problem is particularly challenging due to the arbitrary parameterizations of these surfaces and their varying deformation speeds, necessitating effective spatiotemporal registration. Traditionally, 4D surfac...

We propose the first comprehensive approach for modeling and analyzing the spatiotemporal shape variability in tree-like 4D objects, i.e., 3D objects whose shapes bend, stretch, and change in their branching structure over time as they deform, grow, and interact with their environment. Our key contribution is the representation of tree-like 3D shap...

This paper investigates the role of CLIP image embeddings within the Stable Video Diffusion (SVD) framework, focusing on their impact on video generation quality and computational efficiency. Our findings indicate that CLIP embeddings, while crucial for aesthetic quality, do not significantly contribute towards the subject and background consistenc...

Estimating depth from single RGB images and videos is of widespread interest due to its applications in many areas, including autonomous driving, 3D reconstruction, digital entertainment, and robotics. More than 500 deep learning-based papers have been published in the past 10 years, which indicates the growing interest in the task. This paper pres...

Neural implicit representations have emerged as a powerful paradigm for 3D reconstruction. However, despite their success, existing methods fail to capture fine geometric details and thin structures, especially in scenarios where only sparse RGB views of the objects of interest are available. We hypothesize that current methods for learning neural...

This paper proposes a novel transformer-based framework to generate accurate class-specific object localization maps for weakly supervised semantic segmentation (WSSS). Leveraging the insight that the attended regions of the one-class token in the standard vision transformer can generate class-agnostic localization maps, we investigate the transfor...

As the global population and resource scarcity simultaneously increase, the pressure on plant breeders and growers to maximise the effectiveness of their operations is immense. In this article, we explore the usefulness of image-based data collection and analysis of field experiments consisting of multiple field sites, plant varieties, and treatmen...

Plant disease is one of the major problems in agriculture. Diseases damage plants, reduce yields and lower the quality of the produce. Traditional approaches to detecting plant diseases are usually based on visual inspection and laboratory testing, which can be expensive and time-consuming. They require trained plant pathologists as well as special...

3D point clouds can represent complex 3D objects of arbitrary topologies and with fine‐grained details. They are, however, hard to regress from images using convolutional neural networks, making tasks such as 3D reconstruction from monocular RGB images challenging. In fact, unlike images and volumetric grids, point clouds are unstructured and thus...

This paper proposes a novel transformer-based framework that aims to enhance weakly supervised semantic segmentation (WSSS) by generating accurate class-specific object localization maps as pseudo labels. Building upon the observation that the attended regions of the one-class token in the standard vision transformer can contribute to a class-agnos...

Recent advances in digital technologies have lowered the costs and improved the quality of digital pathology Whole Slide Images (WSI), opening the door to apply Machine Learning (ML) techniques to assist in cancer diagnosis. ML, including Deep Learning (DL), has produced impressive results in diverse image classification tasks in pathology, such as...

Despite extensive research, 3D face reconstruction from a single image remains an open research problem due to the high degree of variability in pose, occlusions and complex lighting conditions. While deep learning-based methods have achieved great success, they are usually limited to near frontal images and images that are free of occlusions. Also...

In stereo vision, self-similar or bland regions can make it difficult to match patches between two images. Active stereo-based methods mitigate this problem by projecting a pseudo-random pattern on the scene so that each patch of an image pair can be identified without ambiguity. However, the projected pattern significantly alters the appearance of...

A major focus of recent developments in stereo vision has been on how to obtain accurate dense disparity maps in passive stereo vision. Active vision systems enable more accurate estimations of dense disparity compared to passive stereo. However, subpixel-accurate disparity estimation remains an open problem that has received little attention. In t...

Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of challenging problems. However, since deep learning methods operate as black boxes, the uncertainty associated with their predictions is often challenging to quantify. Bayesian statistics offer a formalism to understand and quantify the uncertainty associated wit...

Context Most weed species can adversely impact agricultural productivity by competing for nutrients required by high-value crops. Manual weeding is not practical for large cropping areas. Many studies have been undertaken to develop automatic weed management systems for agricultural crops. In this process, one of the major tasks is to recognise the...

We propose a novel framework to learn the spatiotemporal variability in longitudinal 3D shape data sets, which contain observations of objects that evolve and deform over time. This problem is challenging since surfaces come with arbitrary parameterizations and thus, they need to be spatially registered. Also, different deforming objects, hereinaft...

We propose a deep reinforcement learning‐based solution for the 3D reconstruction of objects of complex topologies from a single RGB image. We use a template‐based approach. However, unlike previous template‐based methods, which are limited to the reconstruction of 3D objects of fixed topology, our approach learns simultaneously the geometry and to...

Australia has a reputation for producing a reliable supply of high-quality barley in a contaminant-free climate. As a result, Australian barley is highly sought after by malting, brewing, distilling, and feed industries worldwide. Barley is traded as a variety-specific commodity on the international market for food, brewing and distilling end-use,...

Engagement with upper limb rehabilitation post-stroke can improve rehabilitation outcomes. Virtual Reality can be used to make rehabilitation more engaging. In this paper, we propose a multiple case study to determine: (1) whether game design principles (identified in an earlier study as being likely to engage) actually do engage, in practice, a sa...

Most weed species can adversely impact agricultural productivity by competing for nutrients required by high-value crops. Manual weeding is not practical for large cropping areas. Many studies have been undertaken to develop automatic weed management systems for agricultural crops. In this process, one of the major tasks is to recognise the weeds f...

Cost-based image patch matching is at the core of various techniques in computer vision, photogrammetry and remote sensing. When the subpixel disparity between the reference patch in the source and target images is required, either the cost function or the target image have to be interpolated. While cost-based interpolation is the easiest to implem...

How can one analyze detailed 3D biological objects, such as neurons and botanical trees, that exhibit complex geometrical and topological variation? In this paper, we develop a novel mathematical framework for representing, comparing, and computing geodesic deformations between the shapes of such tree-like 3D objects. A hierarchical organization of...

We propose a novel deep reinforcement learning-based approach for 3D object reconstruction from monocular images. Prior works that use mesh representations are template based. Thus, they are limited to the reconstruction of objects that have the same topology as the template. Methods that use volumetric grids as intermediate representations are com...

The rapid advances in Deep Learning (DL) techniques have enabled rapid detection, localisation, and recognition of objects from images or videos. DL techniques are now being used in many applications related to agriculture and farming. Automatic detection and classification of weeds can play an important role in weed management and so contribute to...

The rapid advances in Deep Learning (DL) techniques have enabled rapid detection, localisation, and recognition of objects from images or videos. DL techniques are now being used in many applications related to agriculture and farming. Automatic detection and classification of weeds can play an important role in weed management and so contribute to...

We propose a novel framework to learn the spatiotemporal variability in longitudinal 3D shape data sets, which contain observations of subjects that evolve and deform over time. This problem is challenging since surfaces come with arbitrary parameterizations and thus, they need to be spatially registered onto each others. Also, different deforming...

We propose a novel framework to learn the spatiotemporal variability in longitudinal 3D shape data sets, which contain observations of subjects that evolve and deform over time. This problem is challenging since surfaces come with arbitrary spatial and temporal parameterizations. Thus, they need to be spatially registered and temporally aligned ont...

Generating textual descriptions of images has been an important topic in computer vision and natural language processing. A number of techniques based on deep learning have been proposed on this topic. These techniques use human-annotated images for training and testing the models. These models require a large number of training data to perform at...

Digital pathology has attracted significant attention in recent years. Analysis of Whole Slide Images (WSIs) is challenging because they are very large, i.e., of Giga-pixel resolution. Identifying Regions of Interest (ROIs) is the first step for pathologists to analyse further the regions of diagnostic interest for cancer detection and other anomal...

Estimating depth from RGB images is a long-standing ill-posed problem, which has been explored for decades by the computer vision, graphics, and machine learning communities. Among the existing techniques, stereo matching remains one of the most widely used in the literature due to its strong connection to the human binocular system. Traditionally,...

In this article, we introduce a family of elastic metrics on the space of parametrized surfaces in 3D space using a corresponding family of metrics on the space of vector-valued one-forms. We provide a numerical framework for the computation of geodesics with respect to these metrics. The family of metrics is invariant under rigid motions and repar...

Digital pathology has attracted significant attention in recent years. Analysis of Whole Slide Images (WSIs) is challenging because they are very large, i.e., of Giga-pixel resolution. Identifying Regions of Interest (ROIs) is the first step for pathologists to analyse further the regions of diagnostic interest for cancer detection and other anomal...

Modern deep learning methods have equipped researchers and engineers with incredibly powerful tools to tackle problems that previously seemed impossible. However, since deep learning methods operate as black boxes, the uncertainty associated with their predictions is often challenging to quantify. Bayesian statistics offer a formalism to understand...

Estimating depth from RGB images is a long-standing ill-posed problem, which has been explored for decades by the computer vision, graphics, and machine learning communities. Among the existing techniques, stereo matching remains one of the most widely used in the literature due to its strong connection to the human binocular system. Traditionally,...

We present an attention-based image captioning method using DenseNet features. Conventional image captioning methods depend on visual information of the whole scene to generate image captions. Such a mechanism often fails to get the information of salient objects and cannot generate semantically correct captions. We consider an attention mechanism...

The root is an important organ of a plant since it is responsible for water and nutrient uptake. Analyzing and modelling variabilities in the geometry and topology of roots can help in assessing the plant's health, understanding its growth patterns, and modeling relations between plant species and between plants and their environment. In this artic...

3D reconstruction is a longstanding ill-posed problem, which has been explored for decades by the computer vision, computer graphics, and machine learning communities. Since 2015, image-based 3D reconstruction using convolutional neural networks (CNN) has attracted increasing interest and demonstrated an impressive performance. Given this new era o...

Object detection from RGB images is a long-standing problem in image processing and computer vision. It has applications in various domains including robotics, surveillance, human–computer interaction, and medical diagnosis. With the availability of low- cost 3D scanners, a large number of RGB-D object detection approaches have been proposed in the...

In this article we introduce a family of elastic metrics on the space of parametrized surfaces in 3D space using a corresponding family of metrics on the space of vector valued one-forms. We provide a numerical framework for the computation of geodesics with respect to these metrics. The family of metrics is invariant under rigid motions and repara...

Object detection from RGB images is a long-standing problem in image processing and computer vision. It has applications in various domains including robotics, surveillance, human-computer interaction, and medical diagnosis. With the availability of low cost 3D scanners, a large number of RGB-D object detection approaches have been proposed in the...

Key message Elite wheat pollinators are critical for successful hybrid breeding. We identified Rht-B1 and Ppd-D1 loci affecting multiple pollinator traits and therefore represent major targets for improving hybrid seed production. Abstract Hybrid breeding has a great potential to significantly boost wheat yields. Ideal male pollinators would be ta...

3D reconstruction is a longstanding ill-posed problem, which has been explored for decades by the computer vision, computer graphics, and machine learning communities. Since 2015, image-based 3D reconstruction using convolutional neural networks (CNN) has attracted increasing interest and demonstrated an impressive performance. Given this new era o...

Estimating depth from RGB images is a long-standing ill-posed problem, which has been explored for decades by the computer vision, graphics, and machine learning communities. In this article, we provide a comprehensive survey of the recent developments in this field. We will focus on the works which use deep learning techniques to estimate depth fr...

Root is an important organ of a plant since it is responsible for water and nutrient uptake. Analyzing and modelling variabilities in the geometry and topology of roots can help in assessing the plant's health, understanding its growth patterns, and modeling relations between plant species and between plants and their environment. In this article,...

In the original publication of this article [1] the authors stated that important resources would be made available online to readers.

Shape is an important physical property of natural and manmade 3D objects that characterizes their external appearances. Understanding differences between shapes and modeling the variability within and across shape classes, hereinafter referred to as \emph{shape analysis}, are fundamental problems to many applications, ranging from computer vision...

Rigid surface registration is a fundamental problem in computer vision. Existing surface registration methods can broadly be divided into two categories: coarse registration and fine registration. This chapter focuses on automatic coarse registration methods. It presents the basic concepts and the representative methods for coarse registration. The...

This chapter reviews the existing 3D acquisition techniques and systems. It particularly discusses the different characteristics that can influence decision making when it comes to selecting a system or a technique that would best suit a given application. The goal of the 3D acquisition task is to collect the geometric samples and possibly the appe...

This chapter introduces some of the fundamental concepts of 3D geometry and 3D geometry processing. It focuses on the concepts that are relevant to the 3D shape analysis tasks. The first part of the chapter covers the elements of differential geometry that are used to describe the local properties of 3D shapes. The second part of the chapter define...

Local shape description is an essential component for many 3D computer vision and graphics applications. This chapter focuses on local descriptors, which, in contrast to global descriptors, encode the shape of small patches around a set of specific keypoints. It presents the challenges and requirements for the design of a 3D keypoint detector and a...

This chapter focuses on the tools and techniques that have been developed for querying 3D model collections using another 3D model as a query. The chapter describes the different datasets and benchmarks, which are currently available in the public domain. It presents the metrics used to evaluate the quality and performance of a 3D retrieval algorit...

This chapter reviews some of the recent advances in 3D face recognition. It first presents the various 3D facial datasets and benchmarks that are currently available to researchers and then discuss the challenges and evaluation criteria. The chapter reviews the key 3D face recognition methods. There are two scenarios of 3D face recognition, namely,...

This chapter reviews some of the methods that incorporate prior knowledge in the process of finding semantic correspondences between 3D shapes. It shows how the problem can be formulated as the optimization of an energy function and compares the different variants of the formulation that have been proposed in the literature. The energy to be minimi...

This chapter focuses on three types of shape modalities, i.e. photos, hand‐drawn sketches and 3D shapes. It reviews the specific challenges and the main datasets which have been used in cross‐domain 3D shape retrieval. The chapter reviews the commonly proposed solutions that handle this new research problem. One of the common approaches used for cr...

This chapter reviews the rich literature of descriptors, which have been proposed for the analysis of the shape of 3D models, and the dissimilarity measures, which have been used to compare them. It focuses on global descriptors, which are grouped into four different categories, namely, distribution‐based, view‐based, spherical representation‐based...

This chapter illustrates the range of applications involving 3D data that have been annotated with some sort of meaning. It considers applications where the 3D data are analyzed to extract usable shapes or properties from the 3D data. The chapter provides examples of semantic applications where the 3D data contribute to the recognition of the gener...

The task of 3D object recognition is to determine, in the presence of clutter and occlusion, the identity and pose (i.e. position and orientation) of an object of interest in a 3D scene. This chapter covers the surface registration‐based 3D object recognition methods. It introduces some recent advances in machine learning‐based 3D object recognitio...

Our journey in the 3D shape analysis world started with the preprocessing techniques, which take raw 3D data and transform them into a state that facilitates their analysis. This book looks at the correspondence and registration problem, which is an important aspect of 3D shape analysis. It is central to many applications including 3D reconstructio...

This chapter describes a set of techniques for finding correspondences and computing registrations between 3D objects, which deform in a nonrigid way. It provides a general formulation and lay down the mathematical framework. The chapter describes some important mathematical concepts and tools on which the methods presented in the chapter are based...

Background Field phenotyping by remote sensing has received increased interest in recent years with the possibility of achieving high-throughput analysis of crop fields. Along with the various technological developments, the application of machine learning methods for image analysis has enhanced the potential for quantitative assessment of a multit...

Generating a description of an image is called image captioning. Image captioning requires to recognize the important objects, their attributes and their relationships in an image. It also needs to generate syntactically and semantically correct sentences. Deep learning-based techniques are capable of handling the complexities and challenges of ima...

Generating a description of an image is called image captioning. Image captioning requires to recognize the important objects, their attributes and their relationships in an image. It also needs to generate syntactically and semantically correct sentences. Deep learning-based techniques are capable of handling the complexities and challenges of ima...

Generating a description of an image is called image captioning. Image captioning requires to recognize the important objects, their attributes and their relationships in an image. It also needs to generate syntactically and semantically correct sentences. Deep learning-based techniques are capable of handling the complexities and challenges of ima...

We propose a framework for statistical modeling of the 3D geometry and topology of botanical trees. We treat botanical trees as points in a tree‐shape space equipped with a proper metric that captures the geometric and the topological differences between trees. Geodesics in the tree‐shape space correspond to the optimal sequence of deformations, i....

We propose a framework for statistical modeling of the 3D geometry and topology of botanical trees. We treat botanical trees as points in a tree-shape space equipped with a proper metric that captures the geometric and the topological differences between trees. Geodesics in the tree-shape space correspond to the optimal sequence of deformations, i....

We propose an algorithm for generating novel 3D tree model variations from existing ones via geometric and structural blending. Our approach is to treat botanical trees as elements of a tree-shape space equipped with a proper metric that quantifies geometric and structural deformations. Geodesics, or shortest paths under the metric, between two poi...

We introduce co-variation analysis as a tool for modeling the way part geometries and configurations co-vary across a family of man-made 3D shapes. While man-made 3D objects exhibit large geometric and structural variations, the geometry, structure, and configuration of their individual components usually do not vary independently from each other b...

Bag of Covariance matrices (BoC) have been recently introduced as an extension of the standard Bag of Words (BoW) to the space of positive semi-definite matrices, which has a Riemannian structure. BoC descriptors can be constructed with various Riemannian metrics and using various quantization approaches. Each construction results in some quantizat...

We propose in this article a new framework for 3D shape retrieval using queries of different modalities, which can include 3D models, images and sketches. The main scientific challenge is that different modalities have different representations and thus lie in different spaces. Moreover, the features that can be extracted from 2D images or 2D sketc...