Search Results

Monocular depth estimation has greatly improved in the recent years but models predicting metric depth still struggle to generalize across diverse camera poses and datasets. While recent supervised methods mitigate this issue by leveraging ground ...

Recent work in Visual Odometry and SLAM has shown the effectiveness of using deep network backbones. Despite excellent accuracy, such approaches are often expensive to run or do not generalize well zero-shot. To address this problem, we introduce ...

Panorama images are popularly used for comprehensive scene understanding due to their integrated field of view. To overcome the spherical image distortions observed in commonly used Equirectangular Projection (ERP) 360-format images, the existing 360 ...

Either RGB images or inertial signals have been used for the task of motion capture (mocap), but combining them together is a new and interesting topic. We believe that the combination is complementary and able to solve the inherent difficulties of using ...

This paper proposes a neural network-based monocular vision ranging method for the situation of large camera calibration and distance variation in monocular vision ranging. The imaging size of the corresponding target under different distances of ...

In order to solve the problems of monocular depth estimation based on deep learning, such as the amount of computation and parameters of deep network architecture is too large and difficult to be applied in engineering equipment, a lightweight end-...

We introduce Vision UFormer (ViUT), a novel deep neural long-range monocular depth estimator. The input is an RGB image, and the output is an image that stores the absolute distance of the object in the scene as its per-pixel values. ...

Display Omitted

• Vision UFormer: Dense depth prediction model combining Vision Transformer with a UNet.

Shape-from-Template (SfT) solves 3D vision from a single image and a deformable 3D object model, called a template. Concretely, SfT computes registration (the correspondence between the template and the image) and reconstruction (the ...

Display Omitted

• DeepSfT is a DNN fully-convolutional based on residual encoder-decoder for SfT.

Deep learning greatly improved the realism of animatable human models by learning geometry and appearance from collections of 3D scans, template meshes, and multi-view imagery. High-resolution models enable photo-realistic avatars but at the cost ...

Detecting 3D objects from monocular RGB images is an ill-posed task for lacking depth knowledge, and monocular-based 3D detection methods perform poorly compared with LiDAR-based 3D detection methods. Some bird’s-eye-view-based monocular 3D ...

In this paper, we present a localization system for the use of drone in a remote laboratory. The objective is to allow a drone to inspect remote electronic instruments autonomously, as well as to return to its base and land on a platform for the ...

We present a method to recover the 3D flying shape of a sail using passive markers. In the navigation and naval architecture domain, retrieving the sail shape may be of immense value to confirm or contest simulation results, and to aid the design ...

Visual-based 3D detection is drawing a lot of attention recently. Despite the best efforts from the computer vision researchers visual-based 3D detection remains a largely unsolved problem. This is primarily due to the lack of accurate depth ...

Perceiving the physical world in 3D is fundamental for self-driving applications. Although temporal motion is an invaluable resource to human vision for detection, tracking, and depth perception, such features have not been thoroughly utilized in ...

Monocular 3D object detection is a challenging task due to unreliable depth, resulting in a distinct performance gap between monocular and LiDAR-based approaches. In this paper, we propose a novel domain adaptation based monocular 3D object ...

• A large-scale multi-view dataset that provides accurate annotations for hand poses.

In this paper, we present a novel deep learning-based architecture, which is under the scope of expert and intelligent systems, to perform accurate real-time tridimensional hand pose estimation using a single RGB frame as an input, so ...

Pose estimation of humanoid objects in monocular systems is a non-trivial problem that has been at the forefront of the human-computer interaction field. The ability for a computer to not only to detect the presence of a humanoid shape within an ...

Using optical head-mounted display (HMD) devices, users can see both real world and Augmented Reality (AR) content simultaneously. AR content can be displayed to both eyes (binocular) or in one eye (monocular).

For a binocular display, users ...

Display Omitted

• A novel exemplar-based algorithm is proposed to implicitly augment the exemplar set.

3D human pose estimation from a single image is a challenging problem due to occlusion, viewpoint variance, and the ill-posed nature of back projection. We follow a standard two-step pipeline which first detects 2D joint locations and ...

This paper presents a structured approach for efficiently exploiting the perspective information of a scene to enhance the detection of objects in monocular systems. It defines a finite grid of 3D positions on the dominant ground plane and computes ...