Related papers: Self-Supervised Correspondence Estimation via Mult…

Visual scene understanding is an important capability that enables robots to purposefully act in their environment. In this paper, we propose a novel approach to object-class segmentation from multiple RGB-D views using deep learning. We…

Aligning partial views of a scene into a single whole is essential to understanding one's environment and is a key component of numerous robotics tasks such as SLAM and SfM. Recent approaches have proposed end-to-end systems that can…

Correspondence search is an essential step in rigid point cloud registration algorithms. Most methods maintain a single correspondence at each step and gradually remove wrong correspondances. However, building one-to-one correspondence with…

The de facto approach in video object-centric learning maintains temporal consistency through learned dynamics modules that predict future object representations, called slots. We demonstrate that these predictors function as expensive…

In this paper we introduce a novel Depth-Aware Video Saliency approach to predict human focus of attention when viewing RGBD videos on regular 2D screens. We train a generative convolutional neural network which predicts a saliency map for…

The 3D localisation of an object and the estimation of its properties, such as shape and dimensions, are challenging under varying degrees of transparency and lighting conditions. In this paper, we propose a method for jointly localising…

While self-supervised learning has enabled effective representation learning in the absence of labels, for vision, video remains a relatively untapped source of supervision. To address this, we propose Pixel-level Correspondence (PiCo), a…

Extracting point correspondences from two or more views of a scene is a fundamental computer vision problem with particular importance for relative camera pose estimation and structure-from-motion. Existing local feature matching…

This letter presents a novel method to estimate the relative poses between RGB-D cameras with minimal overlapping fields of view in a panoramic RGB-D camera system. This calibration problem is relevant to applications such as indoor 3D…

Scene coordinate regression has become an essential part of current camera re-localization methods. Different versions, such as regression forests and deep learning methods, have been successfully applied to estimate the corresponding…

Video colorization task has recently attracted wide attention. Recent methods mainly work on the temporal consistency in adjacent frames or frames with small interval. However, it still faces severe challenge of the inconsistency between…

Many real-world phenomena are observed at multiple resolutions. Predictive models designed to predict these phenomena typically consider different resolutions separately. This approach might be limiting in applications where predictions are…

A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias. While most existing works implicitly achieve this with video-specific pretext tasks (e.g., predicting…

Due to the lack of depth cues in images, multi-frame inputs are important for the success of vision-based perception, prediction, and planning in autonomous driving. Observations from different angles enable the recovery of 3D object states…

Learning feature correspondence is a foundational task in computer vision, holding immense importance for downstream applications such as visual odometry and 3D reconstruction. Despite recent progress in data-driven models, feature…

Predictive models have been at the core of many robotic systems, from quadrotors to walking robots. However, it has been challenging to develop and apply such models to practical robotic manipulation due to high-dimensional sensory…

Across a wide range of applications, from autonomous vehicles to medical imaging, multi-spectral images provide an opportunity to extract additional information not present in color images. One of the most important steps in making this…

Current top-leading solutions for video object segmentation (VOS) typically follow a matching-based regime: for each query frame, the segmentation mask is inferred according to its correspondence to previously processed and the first…

We propose a system that learns to detect objects and infer their 3D poses in RGB-D images. Many existing systems can identify objects and infer 3D poses, but they heavily rely on human labels and 3D annotations. The challenge here is to…

The objective of this paper is self-supervised learning of video object segmentation. We develop a unified framework which simultaneously models cross-frame dense correspondence for locally discriminative feature learning and embeds…