Related papers: HorizonNet: Learning Room Layout with 1D Represent…

Reconstructing 3D human shape and pose from monocular images is challenging despite the promising results achieved by the most recent learning-based methods. The commonly occurred misalignment comes from the facts that the mapping from…

The growing adoption of robotics and augmented reality in real-world applications has driven considerable research interest in 3D object detection based on point clouds. While previous methods address unified training across multiple…

The ultimate goal of this indoor mapping research is to automatically reconstruct a floorplan simply by walking through a house with a smartphone in a pocket. This paper tackles this problem by proposing FloorNet, a novel deep neural…

We present a novel virtual staging application for kitchen remodeling from a single panorama. To ensure the realism of the virtual rendered scene, we capture real-world High Dynamic Range (HDR) panoramas and recover the absolute scene…

In panorama understanding, the widely used equirectangular projection (ERP) entails boundary discontinuity and spatial distortion. It severely deteriorates the conventional CNNs and vision Transformers on panoramas. In this paper, we…

In this work, we introduce the novel problem of identifying dense canonical 3D coordinate frames from a single RGB image. We observe that each pixel in an image corresponds to a surface in the underlying 3D geometry, where a canonical frame…

We introduce DeepNAT, a 3D Deep convolutional neural network for the automatic segmentation of NeuroAnaTomy in T1-weighted magnetic resonance images. DeepNAT is an end-to-end learning-based approach to brain segmentation that jointly learns…

3D indoor scenes are widely used in computer graphics, with applications ranging from interior design to gaming to virtual and augmented reality. They also contain rich information, including room layout, as well as furniture type,…

Reconstructing geometry and topology structures from raw unstructured data has always been an important research topic in indoor mapping research. In this paper, we aim to reconstruct the floorplan with a vectorized representation from…

When using cut-and-paste to acquire a composite image, the geometry inconsistency between foreground and background may severely harm its fidelity. To address the geometry inconsistency in composite images, several existing works learned to…

Fast and robust three-dimensional reconstruction of facial geometric structure from a single image is a challenging task with numerous applications. Here, we introduce a learning-based approach for reconstructing a three-dimensional face…

Determining the 3D orientations of an object in an image, known as single-image pose estimation, is a crucial task in 3D vision applications. Existing methods typically learn 3D rotations parametrized in the spatial domain using Euler…

The objective of this paper is 3D shape understanding from single and multiple images. To this end, we introduce a new deep-learning architecture and loss function, SilNet, that can handle multiple views in an order-agnostic manner. The…

We study end-to-end learning strategies for 3D shape inference from images, in particular from a single image. Several approaches in this direction have been investigated that explore different shape representations and suitable learning…

In this paper, we propose a geometric neural network with edge-aware refinement (GeoNet++) to jointly predict both depth and surface normal maps from a single image. Building on top of two-stream CNNs, GeoNet++ captures the geometric…

Direct image-to-image alignment that relies on the optimization of photometric error metrics suffers from limited convergence range and sensitivity to lighting conditions. Deep learning approaches has been applied to address this problem by…

In 3D face reconstruction, orthogonal projection has been widely employed to substitute perspective projection to simplify the fitting process. This approximation performs well when the distance between camera and face is far enough.…

We present a new latent model of natural images that can be learned on large-scale datasets. The learning process provides a latent embedding for every image in the training dataset, as well as a deep convolutional network that maps the…

The ability to quickly recognize and learn new visual concepts from limited samples enables humans to swiftly adapt to new environments. This ability is enabled by semantic associations of novel concepts with those that have already been…

Bottom-up human pose estimation methods have difficulties in predicting the correct pose for small persons due to challenges in scale variation. In this paper, we present HigherHRNet: a novel bottom-up human pose estimation method for…