Related papers: Sparse Pose Trajectory Completion

In this work we introduce a new self-supervised, semi-parametric approach for synthesizing novel views of a vehicle starting from a single monocular image. Differently from parametric (i.e. entirely learning-based) methods, we show how…

Embodied trajectories, such as the executable motion sequences of robotic manipulators, underwater vehicles, and mobile robots, are a fundamental output of embodied AI. Modern generative models often treat them as a dense, monolithic signal…

Estimating the 6D pose of known objects is important for robots to interact with the real world. The problem is challenging due to the variety of objects as well as the complexity of a scene caused by clutter and occlusions between objects.…

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…

We propose a novel approach to feature point matching, suitable for robust and accurate outdoor visual localization in long-term scenarios. Given a query image, we first match it against a database of registered reference images, using…

Contemporary monocular 6D pose estimation methods can only cope with a handful of object instances. This naturally hampers possible applications as, for instance, robots seamlessly integrated in everyday processes necessarily require the…

When exploring new areas, robotic systems generally exclusively plan and execute controls over geometry that has been directly measured. When entering space that was previously obstructed from view such as turning corners in hallways or…

Understanding 3D object shapes necessitates shape representation by object parts abstracted from results of instance and semantic segmentation. Promising shape representations enable computers to interpret a shape with meaningful parts and…

In the absence of a mechanical stabilizer, the camera undergoes inevitable rotational dynamics during capturing, which induces perspective-based blur especially under long-exposure scenarios. From an optical standpoint, perspective-based…

State-of-the-art object pose estimation handles multiple instances in a test image by using multi-model formulations: detection as a first stage and then separately trained networks per object for 2D-3D geometric correspondence prediction…

Despite significant progress, RGB-based trackers remain vulnerable to challenging imaging conditions, such as low illumination and fast motion. Event cameras offer a promising alternative by asynchronously capturing pixel-wise brightness…

Current 6D object pose estimation methods usually require a 3D model for each object. These methods also require additional training in order to incorporate new objects. As a result, they are difficult to scale to a large number of objects…

Reconstructing the motion of objects from videos is a key component for embodied AI and robot manipulation. While diverse approaches to object pose tracking have been studied, they rely heavily on strong external priors, such as depth data…

We demonstrate that frequently appearing objects can be discovered by training randomly sampled patches from a small number of images (100 to 200) by self-supervision. Key to this approach is the pattern space, a latent space of patterns…

Self-supervised representation learning techniques utilize large datasets without semantic annotations to learn meaningful, universal features that can be conveniently transferred to solve a wide variety of downstream supervised tasks. In…

This paper addresses the task of estimating the 6 degrees of freedom pose of a known 3D object from depth information represented by a point cloud. Deep features learned by convolutional neural networks from color information have been the…

We present a method for human pose tracking that is based on learning spatiotemporal relationships among joints. Beyond generating the heatmap of a joint in a given frame, our system also learns to predict the offset of the joint from a…

We propose a method at the intersection of Computer Vision and Computer Graphics fields, which automatically generates RGBD images using neural networks, based on previously seen and synchronized video, depth and pose signals. Since the…

We present a technique for synthesizing a motion blurred image from a pair of unblurred images captured in succession. To build this system we motivate and design a differentiable "line prediction" layer to be used as part of a neural…

In this paper, we address the problem of learning 3D human pose and body shape from 2D image dataset, without having to use 3D dataset (body shape and pose). The idea is to use dense correspondences between image points and a body surface,…