Related papers: Canonical Capsules: Self-Supervised Capsules in Ca…

3D reconstruction from 2D inputs, especially for non-rigid objects like humans, presents unique challenges due to the significant range of possible deformations. Traditional methods often struggle with non-rigid shapes, which require…

3D point cloud analysis has drawn a lot of research attention due to its wide applications. However, collecting massive labelled 3D point cloud data is both time-consuming and labor-intensive. This calls for data-efficient learning methods.…

Understanding the 3D world without supervision is currently a major challenge in computer vision as the annotations required to supervise deep networks for tasks in this domain are expensive to obtain on a large scale. In this paper, we…

3D point cloud semantic and instance segmentation is crucial and fundamental for 3D scene understanding. Due to the complex structure, point sets are distributed off balance and diversely, which appears as both category imbalance and…

3D object detection is an important task in computer vision. Most existing methods require a large number of high-quality 3D annotations, which are expensive to collect. Especially for outdoor scenes, the problem becomes more severe due to…

3D object detection has attracted much attention thanks to the advances in sensors and deep learning methods for point clouds. Current state-of-the-art methods like VoteNet regress direct offset towards object centers and box orientations…

Invariance against rotations of 3D objects is an important property in analyzing 3D point set data. Conventional 3D point set DNNs having rotation invariance typically obtain accurate 3D shape features via supervised learning by using…

We address the key question of how object part representations can be found from the internal states of CNNs that are trained for high-level tasks, such as object classification. This work provides a new unsupervised method to learn…

In a constant evolving world, change detection is of prime importance to keep updated maps. To better sense areas with complex geometry (urban areas in particular), considering 3D data appears to be an interesting alternative to classical…

Semi-supervised learning (SSL), thanks to the significant reduction of data annotation costs, has been an active research topic for large-scale 3D scene understanding. However, the existing SSL-based methods suffer from severe training…

Accurate 3D object detection in LiDAR point clouds is crucial for autonomous driving systems. To achieve state-of-the-art performance, the supervised training of detectors requires large amounts of human-annotated data, which is expensive…

The task of point cloud upsampling aims to acquire dense and uniform point sets from sparse and irregular point sets. Although significant progress has been made with deep learning models, state-of-the-art methods require ground-truth dense…

We present a method to learn single-view reconstruction of the 3D shape, pose, and texture of objects from categorized natural images in a self-supervised manner. Since this is a severely ill-posed problem, carefully designing a training…

Point cloud completion aims to reconstruct complete shapes from partial observations. Although current methods have achieved remarkable performance, they still have some limitations: Supervised methods heavily rely on ground truth, which…

Learning invariant representations has been the long-standing approach to self-supervised learning. However, recently progress has been made in preserving equivariant properties in representations, yet do so with highly prescribed…

Spatial reasoning on multi-view line drawings by state-of-the-art supervised deep networks is recently shown with puzzling low performances on the SPARE3D dataset. Based on the fact that self-supervised learning is helpful when a large…

Annotating large-scale point clouds is highly time-consuming and often infeasible for many complex real-world tasks. Point cloud pre-training has therefore become a promising strategy for learning discriminative representations without…

The past few years have witnessed the great success and prevalence of self-supervised representation learning within the language and 2D vision communities. However, such advancements have not been fully migrated to the field of 3D point…

Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots. Slot-based auto-encoders stand out as a prominent method for this task. Within them, crucial aspects include guiding the encoder…

Self-supervised methods have shown remarkable progress in learning high-level semantics and low-level temporal correspondence. Building on these results, we take one step further and explore the possibility of integrating these two features…