Related papers: Denoise and Contrast for Category Agnostic Shape C…

Although unsupervised feature learning has demonstrated its advantages to reducing the workload of data labeling and network design in many fields, existing unsupervised 3D learning methods still cannot offer a generic network for various…

Image-based object pose estimation sounds amazing because in real applications the shape of object is oftentimes not available or not easy to take like photos. Although it is an advantage to some extent, un-explored shape information in 3D…

Representing complex 3D objects as simple geometric primitives, known as shape abstraction, is important for geometric modeling, structural analysis, and shape synthesis. In this paper, we propose an unsupervised shape abstraction method to…

We propose a data-driven method for recovering miss-ing parts of 3D shapes. Our method is based on a new deep learning architecture consisting of two sub-networks: a global structure inference network and a local geometry refinement…

Motivated by the intuition that one can transform two aligned point clouds to each other more easily and meaningfully than a misaligned pair, we propose CorrNet3D -- the first unsupervised and end-to-end deep learning-based framework -- to…

Category-agnostic pose estimation (CAPE) aims to predict keypoints for arbitrary classes given a few support images annotated with keypoints. Existing methods only rely on the features extracted at support keypoints to predict or refine the…

Unsupervised disentangled representation learning is a long-standing problem in computer vision. This work proposes a novel framework for performing image clustering from deep embeddings by combining instance-level contrastive learning with…

As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on various downstream tasks. However, the trend of large-scale…

Meta-learning has emerged as an efficient approach for constructing target models based on support sets. For example, the meta-learned embeddings enable the construction of target nearest-neighbor classifiers for specific tasks by pulling…

Partially-supervised instance segmentation is a task which requests segmenting objects from novel unseen categories via learning on limited seen categories with annotated masks thus eliminating demands of heavy annotation burden. The key to…

3D anomaly detection targets the detection and localization of defects in 3D point clouds trained solely on normal data. While a unified model improves scalability by learning across multiple categories, it often suffers from Inter-Category…

Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component,…

We propose a unified point cloud video self-supervised learning framework for object-centric and scene-centric data. Previous methods commonly conduct representation learning at the clip or frame level and cannot well capture fine-grained…

Point cloud completion aims to recover the complete shape based on a partial observation. Existing methods require either complete point clouds or multiple partial observations of the same object for learning. In contrast to previous…

Arguably one of the top success stories of deep learning is transfer learning. The finding that pre-training a network on a rich source set (eg., ImageNet) can help boost performance once fine-tuned on a usually much smaller target set, has…

Unsupervised depth completion aims to recover dense depth from the sparse one without using the ground-truth annotation. Although depth measurement obtained from LiDAR is usually sparse, it contains valid and real distance information,…

Though deep learning methods have shown great success in 3D point cloud part segmentation, they generally rely on a large volume of labeled training data, which makes the model suffer from unsatisfied generalization abilities to unseen…

Estimating correspondences between pairs of non-rigid deformable 3D shapes remains a significant challenge in computer vision and graphics. While deep functional map methods have become the go-to solution for addressing this problem, they…

Deep features are a cornerstone of computer vision research, capturing image semantics and enabling the community to solve downstream tasks even in the zero- or few-shot regime. However, these features often lack the spatial resolution to…

Automated surface inspection is an important task in many manufacturing industries and often requires machine learning driven solutions. Supervised approaches, however, can be challenging, since it is often difficult to obtain large amounts…