Related papers: Dense RepPoints: Representing Visual Objects with …

Estimating the 6-DoF pose of a rigid object from a single RGB image is a crucial yet challenging task. Recent studies have shown the great potential of dense correspondence-based solutions, yet improvements are still needed to reach…

3D dense reconstruction refers to the process of obtaining the complete shape and texture features of 3D objects from 2D planar images. 3D reconstruction is an important and extensively studied problem, but it is far from being solved. This…

We introduce a method for high-quality 3D reconstruction from multi-view images. Our method uses a new point-based representation, the regularized dipole sum, which generalizes the winding number to allow for interpolation of per-point…

Dense 3D visual mapping estimates as many as possible pixel depths, for each image. This results in very dense point clouds that often contain redundant and noisy information, especially for surfaces that are roughly planar, for instance,…

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…

Object counting, whose aim is to estimate the number of objects from a given image, is an important and challenging computation task. Significant efforts have been devoted to addressing this problem and achieved great progress, yet counting…

Being able to grasp objects is a fundamental component of most robotic manipulation systems. In this paper, we present a new approach to simultaneously reconstruct a mesh and a dense grasp quality map of an object from a depth image. At the…

This paper presents DENSER, an efficient and effective approach leveraging 3D Gaussian splatting (3DGS) for the reconstruction of dynamic urban environments. While several methods for photorealistic scene representations, both implicitly…

For many applications, we need to use techniques to represent convex shapes and objects. In this work, we use level set method to represent shapes and find a necessary and sufficient condition on the level set function to guarantee the…

We propose a new representation of visual data that disentangles object position from appearance. Our method, termed Deep Latent Particles (DLP), decomposes the visual input into low-dimensional latent ``particles'', where each particle is…

Existing neural field representations for 3D object reconstruction either (1) utilize object-level representations, but suffer from low-quality details due to conditioning on a global latent code, or (2) are able to perfectly reconstruct…

Dense 3D correspondence can enhance robotic manipulation by enabling the generalization of spatial, functional, and dynamic information from one object to an unseen counterpart. Compared to shape correspondence, semantic correspondence is…

Semantic segmentation, which refers to pixel-wise classification of an image, is a fundamental topic in computer vision owing to its growing importance in robot vision and autonomous driving industries. It provides rich information about…

While witnessed with rapid development, remote sensing object detection remains challenging for detecting high aspect ratio objects. This paper shows that large strip convolutions are good feature representation learners for remote sensing…

In this thesis, we develop various techniques for working with sets in machine learning. Each input or output is not an image or a sequence, but a set: an unordered collection of multiple objects, each object described by a feature vector.…

By considering the spatial correspondence, dense self-supervised representation learning has achieved superior performance on various dense prediction tasks. However, the pixel-level correspondence tends to be noisy because of many similar…

Keypoint detection is the foundation of many computer vision tasks, including image registration, structure-from-motion, 3D reconstruction, visual odometry, and SLAM. Traditional detectors (SIFT, ORB, BRISK, FAST, etc.) and learning-based…

Contrastive learning methods for unsupervised visual representation learning have reached remarkable levels of transfer performance. We argue that the power of contrastive learning has yet to be fully unleashed, as current methods are…

Nowadays, many visual scene understanding problems are addressed by dense prediction networks. But pixel-wise dense annotations are very expensive (e.g., for scene parsing) or impossible (e.g., for intrinsic image decomposition), motivating…

We present a new point-based approach for modeling the appearance of real scenes. The approach uses a raw point cloud as the geometric representation of a scene, and augments each point with a learnable neural descriptor that encodes local…