Related papers: True 3D imaging with monocular cues using holograp…
We examine the nature of the 3D image as obtained by replay (or back-propagation) of the object wave from the hologram recording plane to the original object volume. While recording of a hologram involves transferring information from a 3D…
Monocular depth estimation, enabled by self-supervised learning, is a key technique for 3D perception in computer vision. However, it faces significant challenges in real-world scenarios, which encompass adverse weather variations, motion…
Stereoscopic 3D (S3D) displays provide an additional sense of depth compared to non-stereoscopic displays by sending slightly different images to the two eyes. But conventional S3D displays do not reproduce all natural depth cues. In…
Monocular depth estimation is a recurring subject in the field of computer vision. Its ability to describe scenes via a depth map while reducing the constraints related to the formulation of perspective geometry tends to favor its use.…
Scale-aware monocular depth estimation poses a significant challenge in computer-aided endoscopic navigation. However, existing depth estimation methods that do not consider the geometric priors struggle to learn the absolute scale from…
Human motion recovery for real-world interaction demands both precise action details and metric-scale trajectories. Recovering absolute human pose from monocular input presents a viable solution, but faces two main challenges: (1) models'…
We propose a novel geometric and photometric 3D mapping pipeline for accurate and real-time scene reconstruction from monocular images. To achieve this, we leverage recent advances in dense monocular SLAM and real-time hierarchical…
Is it possible to realize a holographic display with commercial available components and devices? Is it possible to manipulate light to reconstruct light field without using coherent light and complicated optical components? Is it possible…
Geometric reconstruction and SLAM with endoscopic images have advanced significantly in recent years. In most medical fields, monocular endoscopes are employed, and the algorithms used are typically adaptations of those designed for…
Scene flow estimation is an extremely important task in computer vision to support the perception of dynamic changes in the scene. For robust scene flow, learning-based approaches have recently achieved impressive results using either…
Current self-supervised methods for monocular depth estimation are largely based on deeply nested convolutional networks that leverage stereo image pairs or monocular sequences during a training phase. However, they often exhibit inaccurate…
3D object detection from monocular images is an ill-posed problem due to the projective entanglement of depth and scale. To overcome this ambiguity, we present a novel self-supervised method for textured 3D shape reconstruction and pose…
Monocular SLAM has received a lot of attention due to its simple RGB inputs and the lifting of complex sensor constraints. However, existing monocular SLAM systems are designed for bounded scenes, restricting the applicability of SLAM…
Generating accurate 3D reconstructions from endoscopic video is a promising avenue for longitudinal radiation-free analysis of sinus anatomy and surgical outcomes. Several methods for monocular reconstruction have been proposed, yielding…
Monocular 3D face reconstruction is a wide-spread topic, and existing approaches tackle the problem either through fast neural network inference or offline iterative reconstruction of face geometry. In either case carefully-designed energy…
Existing methods for reconstructing objects and humans from a monocular image suffer from severe mesh collisions and performance limitations for interacting occluding objects. This paper introduces a method to obtain a globally consistent…
Metasurface-generated holography has emerged as a promising route for fully reproducing vivid scenes by manipulating the optical properties of light using ultra-compact devices. However, achieving multiple holographic images using a single…
The bundle of geometry and appearance in computer vision has proven to be a promising solution for robots across a wide variety of applications. Stereo cameras and RGB-D sensors are widely used to realise fast 3D reconstruction and…
Holographic near-eye displays offer unprecedented capabilities for virtual and augmented reality systems, including perceptually important focus cues. Although artificial intelligence--driven algorithms for computer-generated holography…
Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physically plausible 3D scene from a single monocular RGB image.…