Related papers: Accurate Grid Keypoint Learning for Efficient Vide…

Extracting informative representations from videos is fundamental for effectively learning various downstream tasks. We present a novel approach for unsupervised learning of meaningful representations from videos, leveraging the concept of…

In this work we introduce a time- and memory-efficient method for structured prediction that couples neuron decisions across both space at time. We show that we are able to perform exact and efficient inference on a densely connected…

Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…

Efficient neural representations for dynamic video scenes are critical for applications ranging from video compression to interactive simulations. Yet, existing methods often face challenges related to high memory usage, lengthy training…

In this work, we address the challenging video scene parsing problem by developing effective representation learning methods given limited parsing annotations. In particular, we contribute two novel methods that constitute a unified parsing…

Point clouds are naturally sparse, while image pixels are dense. The inconsistency limits feature fusion from both modalities for point-wise scene flow estimation. Previous methods rarely predict scene flow from the entire point clouds of…

Contemporary grasp detection approaches employ deep learning to achieve robustness to sensor and object model uncertainty. The two dominant approaches design either grasp-quality scoring or anchor-based grasp recognition networks. This…

Despite significant progress in image-based 3D scene flow estimation, the performance of such approaches has not yet reached the fidelity required by many applications. Simultaneously, these applications are often not restricted to…

A robot's ability to act is fundamentally constrained by what it can perceive. Many existing approaches to visual representation learning utilize general-purpose training criteria, e.g. image reconstruction, smoothness in latent space, or…

Video prediction is commonly referred to as forecasting future frames of a video sequence provided several past frames thereof. It remains a challenging domain as visual scenes evolve according to complex underlying dynamics, such as the…

The irregularity and permutation invariance of point cloud data pose challenges for effective learning. Conventional methods for addressing this issue involve converting raw point clouds to intermediate representations such as 3D voxel…

Object 6D pose estimation is an important research topic in the field of computer vision due to its wide application requirements and the challenges brought by complexity and changes in the real-world. We think fully exploring the…

Video prediction is a challenging computer vision task that has a wide range of applications. In this work, we present a new family of Transformer-based models for video prediction. Firstly, an efficient local spatial-temporal separation…

We address the problem of keypoint selection, and find that the performance of 6DoF pose estimation methods can be improved when pre-defined keypoint locations are learned, rather than being heuristically selected as has been the standard…

This paper presents a novel hybrid representation learning framework for streaming data, where an image frame in a video is modeled by an ensemble of two distinct deep neural networks; one is a low-bit quantized network and the other is a…

This paper presents a novel keypoints-based attention mechanism for visual recognition in still images. Deep Convolutional Neural Networks (CNNs) for recognizing images with distinctive classes have shown great success, but their…

Stochastic video prediction enables the consideration of uncertainty in future motion, thereby providing a better reflection of the dynamic nature of the environment. Stochastic video prediction methods based on image auto-regressive…

Event cameras are vision sensors that record asynchronous streams of per-pixel brightness changes, referred to as "events". They have appealing advantages over frame-based cameras for computer vision, including high temporal resolution,…

This paper describes recent developments in object specific pose and shape prediction from single images. The main contribution is a new approach to camera pose prediction by self-supervised learning of keypoints corresponding to locations…

Video prediction is a fundamental task for various downstream applications, including robotics and world modeling. Although general video prediction models have achieved remarkable performance in standard scenarios, occlusion is still an…