相关论文: StrobeNet: Category-Level Multiview Reconstruction…

Three-dimensional (3D) object reconstruction based on differentiable rendering (DR) is an active research topic in computer vision. DR-based methods minimize the difference between the rendered and target images by optimizing both the shape…

During 3D reconstruction, it is often the case that people cannot scan each individual object from all views, resulting in missing geometry in the captured scan. This missing geometry can be fundamentally limiting for many applications,…

We propose a novel 3d shape representation for 3d shape reconstruction from a single image. Rather than predicting a shape directly, we train a network to generate a training set which will be fed into another learning algorithm to define…

This paper focuses on the challenging task of learning 3D object surface reconstructions from RGB images. Existingmethods achieve varying degrees of success by using different surface representations. However, they all have their own…

We propose a method that efficiently learns distributions over articulation model parameters directly from depth images without the need to know articulation model categories a priori. By contrast, existing methods that learn articulation…

Image classification models often demonstrate unstable performance in real-world applications due to variations in image information, driven by differing visual perspectives of subject objects and lighting discrepancies. To mitigate these…

The ability to estimate joint parameters is essential for various applications in robotics and computer vision. In this paper, we propose CAPT: category-level articulation estimation from a point cloud using Transformer. CAPT uses an…

Recently, learning frameworks have shown the capability of inferring the accurate shape, pose, and texture of an object from a single RGB image. However, current methods are trained on image collections of a single category in order to…

In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images. To achieve high-quality images,…

We develop a model of perceptual similarity judgment based on re-training a deep convolution neural network (DCNN) that learns to associate different views of each 3D object to capture the notion of object persistence and continuity in our…

We consider the problem of 3D shape reconstruction from multi-modal data, given uncertain calibration parameters. Typically, 3D data modalities can be in diverse forms such as sparse point sets, volumetric slices, 2D photos and so on. To…

In this paper, we tackle a new task of 3D object synthesis, where a 3D model is composited with another object category to create a novel 3D model. However, most existing text/image/3D-to-3D methods struggle to effectively integrate…

We present a technique for a complete 3D reconstruction of small objects moving in front of a textured background. It is a particular variation of multibody structure from motion, which specializes to two objects only. The scene is captured…

We present an approach to matching images of objects in fine-grained datasets without using part annotations, with an application to the challenging problem of weakly supervised single-view reconstruction. This is in contrast to prior works…

Semantic scene understanding from point clouds is particularly challenging as the points reflect only a sparse set of the underlying 3D geometry. Previous works often convert point cloud into regular grids (e.g. voxels or bird-eye view…

This paper addresses the problem of reconstructing a scene online at the level of objects given an RGB-D video sequence. While current object-aware neural implicit representations hold promise, they are limited in online reconstruction…

This work considers a new task in geometric deep learning: generating a triangulation among a set of points in 3D space. We present PointTriNet, a differentiable and scalable approach enabling point set triangulation as a layer in 3D…

We present HOReeNet, which tackles the novel task of manipulating images involving hands, objects, and their interactions. Especially, we are interested in transferring objects of source images to target images and manipulating 3D hand…

A key requirement for leveraging supervised deep learning methods is the availability of large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very little data is available -- current datasets cover a small…

Spatiotemporal feature learning in videos is a fundamental problem in computer vision. This paper presents a new architecture, termed as Appearance-and-Relation Network (ARTNet), to learn video representation in an end-to-end manner.…