Related papers: Sphere2Vec: A General-Purpose Location Representat…

We infer and generate three-dimensional (3D) scene information from a single input image and without supervision. This problem is under-explored, with most prior work relying on supervision from, e.g., 3D ground-truth, multiple images of a…

Camera-based 3D Semantic Scene Completion (SSC) is a critical task in autonomous driving systems, assessing voxel-level geometry and semantics for holistic scene perception. While existing voxel-based and plane-based SSC methods have…

The advances in AI-enabled techniques have accelerated the creation and automation of visualizations in the past decade. However, presenting visualizations in a descriptive and generative format remains a challenge. Moreover, current…

With the advancement of remote-sensed imaging large volumes of very high resolution land cover images can now be obtained. Automation of object recognition in these 2D images, however, is still a key issue. High intra-class variance and low…

Linear encoding of sparse vectors is widely popular, but is commonly data-independent -- missing any possible extra (but a priori unknown) structure beyond sparsity. In this paper we present a new method to learn linear encoders that adapt…

The recent success of implicit neural scene representations has presented a viable new method for how we capture and store 3D scenes. Unlike conventional 3D representations, such as point clouds, which explicitly store scene properties in…

Transformer-based methods have swept the benchmarks on 2D and 3D detection on images. Because tokenization before the attention mechanism drops the spatial information, positional encoding becomes critical for those methods. Recent works…

Developing deep learning techniques for geometric data is an active and fruitful research area. This paper tackles the problem of sphere-type surface learning by developing a novel surface-to-image representation. Using this representation…

Object recognition has seen significant progress in the image domain, with focus primarily on 2D perception. We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an…

Modern visual world modeling systems increasingly rely on high-capacity architectures and large-scale data to produce plausible motion, yet they often fail to preserve underlying 3D geometry or physically consistent camera dynamics. A key…

In this paper, we develop a novel method for fast geodesic distance queries. The key idea is to embed the mesh into a high-dimensional space, such that the Euclidean distance in the high-dimensional space can induce the geodesic distance in…

Hyperdimensional computing (HDC) is an emerging computing paradigm that imitates the brain's structure to offer a powerful and efficient processing and learning model. In HDC, the data are encoded with long vectors, called hypervectors,…

Shape completion, a crucial task in 3D computer vision, involves predicting and filling the missing regions of scanned or partially observed objects. Current methods expect known pose or canonical coordinates and do not perform well under…

This paper presents the Visual Place Cell Encoding (VPCE) model, a biologically inspired computational framework for simulating place cell-like activation using visual input. Drawing on evidence that visual landmarks play a central role in…

Attention-based encoder-decoder framework is widely used in the scene text recognition task. However, for the current state-of-the-art(SOTA) methods, there is room for improvement in terms of the efficient usage of local visual and global…

Part-level point cloud segmentation has recently attracted significant attention in 3D computer vision. Nevertheless, existing research is constrained by two major challenges: native 3D models lack generalization due to data scarcity, while…

Visual localization (VL) is the task of estimating the camera pose in a known scene. VL methods, a.o., can be distinguished based on how they represent the scene, e.g., explicitly through a (sparse) point cloud or a collection of images or…

Geometry problem-solving remains a significant challenge for Large Multimodal Models (LMMs), requiring not only global shape recognition but also attention to intricate local relationships related to geometric theory. To address this, we…

We introduce a framework for learning latent representations of 4D objects which are descriptive, faithfully capturing object geometry and appearance; compressive, aiding in downstream efficiency; and accessible, requiring minimal input,…

Existing self-supervised learning (SSL) methods primarily learn object-invariant representations but often neglect the spatial structure and relationships among object parts. To address this limitation, we introduce Spatial Prediction (SP),…