Related papers: 4DContrast: Contrastive Learning with Dynamic Corr…

The success of Transformer-based models has encouraged many researchers to learn CAD models using sequence-based approaches. However, learning CAD models is still a challenge, because they can be represented as complex shapes with long…

Contrastive, self-supervised learning of object representations recently emerged as an attractive alternative to reconstruction-based training. Prior approaches focus on contrasting individual object representations (slots) against one…

As part of human core knowledge, the representation of objects is the building block of mental representation that supports high-level concepts and symbolic reasoning. While humans develop the ability of perceiving objects situated in 3D…

We introduce Consistent Instance Field, a continuous and probabilistic spatio-temporal representation for dynamic scene understanding. Unlike prior methods that rely on discrete tracking or view-dependent features, our approach disentangles…

In recent years, contrastive learning achieves impressive results on self-supervised visual representation learning, but there still lacks a rigorous understanding of its learning dynamics. In this paper, we show that if we cast a…

The recent success in human action recognition with deep learning methods mostly adopt the supervised learning paradigm, which requires significant amount of manually labeled data to achieve good performance. However, label collection is an…

Recently, cross domain transfer has been applied for unsupervised image restoration tasks. However, directly applying existing frameworks would lead to domain-shift problems in translated images due to lack of effective supervision.…

Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudo labels as supervision and use the learned representations for several…

We present a new pipeline for holistic 3D scene understanding from a single image, which could predict object shapes, object poses, and scene layout. As it is a highly ill-posed problem, existing methods usually suffer from inaccurate…

Instance segmentation in 3D is a challenging task due to the lack of large-scale annotated datasets. In this paper, we show that this task can be addressed effectively by leveraging instead 2D pre-trained models for instance segmentation.…

The use of pretrained deep neural networks represents an attractive way to achieve strong results with few data available. When specialized in dense problems such as object detection, learning local rather than global information in images…

Current approaches to semantic image and scene understanding typically employ rather simple object representations such as 2D or 3D bounding boxes. While such coarse models are robust and allow for reliable object detection, they discard…

Unsupervised domain adaptation which aims to adapt models trained on a labeled source domain to a completely unlabeled target domain has attracted much attention in recent years. While many domain adaptation techniques have been proposed…

Semantic segmentation in autonomous driving predominantly focuses on learning from large-scale data with a closed set of known classes without considering unknown objects. Motivated by safety reasons, we address the video class agnostic…

The unsupervised 3D object detection is to accurately detect objects in unstructured environments with no explicit supervisory signals. This task, given sparse LiDAR point clouds, often results in compromised performance for detecting…

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…

This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation.…

Humans can naturally identify and mentally complete occluded objects in cluttered environments. However, imparting similar cognitive ability to robotics remains challenging even with advanced reconstruction techniques, which models scenes…

This paper explores self-supervised learning of amodal 3D feature representations from RGB and RGB-D posed images and videos, agnostic to object and scene semantic content, and evaluates the resulting scene representations in the downstream…

In this paper, we propose a self-supervised learningmethod for multi-object pose estimation. 3D object under-standing from 2D image is a challenging task that infers ad-ditional dimension from reduced-dimensional information.In particular,…