Related papers: Few-shot Single-view 3D Reconstruction with Memory…

Reconstructing 3D shapes from a single image plays an important role in computer vision. Many methods have been proposed and achieve impressive performance. However, existing methods mainly focus on extracting semantic information from…

Mainstream 3D representation learning approaches are built upon contrastive or generative modeling pretext tasks, where great improvements in performance on various downstream tasks have been achieved. However, we find these two paradigms…

Recovering 3D face models from 2D in-the-wild images has gained considerable attention in the computer vision community due to its wide range of potential applications. However, the lack of ground-truth labeled datasets and the complexity…

The use of meta-learning and transfer learning in the task of few-shot image classification is a well researched area with many papers showcasing the advantages of transfer learning over meta-learning in cases where data is plentiful and…

Current CNN-based algorithms for recovering the 3D pose of an object in an image assume knowledge about both the object category and its 2D localization in the image. In this paper, we relax one of these constraints and propose to solve the…

Recent research has seen numerous supervised learning-based methods for 3D shape segmentation and remarkable performance has been achieved on various benchmark datasets. These supervised methods require a large amount of annotated data to…

Continual learning has been extensively studied for classification tasks with methods developed to primarily avoid catastrophic forgetting, a phenomenon where earlier learned concepts are forgotten at the expense of more recent samples. In…

Metric-based few-shot learning methods concentrate on learning transferable feature embedding that generalizes well from seen categories to unseen categories under the supervision of limited number of labelled instances. However, most of…

Recent advances in self-supervised learning have attracted significant attention from both machine learning and neuroscience. This is primarily because self-supervised methods do not require annotated supervisory information, making them…

We present a novel learning approach to recover the 6D poses and sizes of unseen object instances from an RGB-D image. To handle the intra-class shape variation, we propose a deep network to reconstruct the 3D object model by explicitly…

The structured light (SL)-based three-dimensional (3D) measurement techniques with deep learning have been widely studied to improve measurement efficiency, among which fringe projection profilometry (FPP) and speckle projection…

Humans are capable of learning new concepts from small numbers of examples. In contrast, supervised deep learning models usually lack the ability to extract reliable predictive rules from limited data scenarios when attempting to classify…

Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. However, a major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression, a…

This paper studies the complex task of simultaneous multi-object 3D reconstruction, 6D pose and size estimation from a single-view RGB-D observation. In contrast to instance-level pose estimation, we focus on a more challenging problem…

Recently, deep learning-based compressed sensing (CS) has achieved great success in reducing the sampling and computational cost of sensing systems and improving the reconstruction quality. These approaches, however, largely overlook the…

Conventional methods for object detection usually require substantial amounts of training data and annotated bounding boxes. If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize.…

We present a unified framework tackling two problems: class-specific 3D reconstruction from a single image, and generation of new 3D shape samples. These tasks have received considerable attention recently; however, most existing approaches…

To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with limited bounding box annotations. To this end, we first observe…

Traditional fine-grained image classification typically relies on large-scale training samples with annotated ground-truth. However, some sub-categories have few available samples in real-world applications, and current few-shot models…

We present a self-supervised learning approach to learning monocular 3D face reconstruction with a pose guidance network (PGN). First, we unveil the bottleneck of pose estimation in prior parametric 3D face learning methods, and propose to…