相关论文: Differential Methods in Catadioptric Sensor Design…

In modern computer vision, the optimal representation of 3D shape continues to be task-dependent. One fundamental operation applied to such representations is differentiable rendering, as it enables inverse graphics approaches in learning…

For a plane symmetric object we can find two views - mirrored at the plane of symmetry - that will yield the exact same image of that object. In consequence, having one image of a plane symmetric object and a calibrated camera, we can…

Differentiable rendering is a technique to connect 3D scenes with corresponding 2D images. Since it is differentiable, processes during image formation can be learned. Previous approaches to differentiable rendering focus on mesh-based…

Light field applications, especially light field rendering and depth estimation, developed rapidly in recent years. While state-of-the-art light field rendering methods handle semi-transparent and reflective objects well, depth estimation…

We investigate methods for determining if a planar surface contains geometric deviations (e.g., protrusions, objects, divots, or cliffs) using only an instantaneous measurement from a miniature optical time-of-flight sensor. The key to our…

We present a method for handling view-dependent information in radiance fields to help with convergence and quality of 3D reconstruction. Radiance fields with view-dependence suffers from the so called shape-radiance ambiguity, which can…

Virtual reality (VR) renderers driving CAVEs and similar immersive environments use the off-axis stereo camera model so that a tracked user can move freely in front of the projection plane. Geometrically, off-axis projection results in…

Optical images of transparent three-dimensional objects can be different from a replica of the object's cross section in the image plane due to refraction at the surface or in the body of the object. Simulations of the object's image are…

An image-based technique for measuring the complex field in the pupil of an imaging system is presented. Two point source images, one with a small modification introduced in the pupil, are combined using a simple and non-iterative…

We present a technique for Stereoscopic Cylindrical Screen (SCS) Projection of a world scene to a 360-degree canvas for viewing with 3D glasses. To optimize the rendering pipeline, we render the scene to four cubemaps, before sampling…

Accurately measuring the geometry and spatially-varying reflectance of real-world objects is a complex task due to their intricate shapes formed by concave features, hollow engravings and diverse surfaces, resulting in inter-reflection and…

Numerous vector angular spectrum methods have been presented to model the vectorial nature of diffractive electromagnetic field, facilitating optical field engineering in polarization-related and high numerical aperture systems. However,…

Photometric stereo is a method for estimating the normal vectors of an object from images of the object under varying lighting conditions. Motivated by several recent works that extend photometric stereo to more general objects and lighting…

High-resolution tactile sensors have become critical for embodied perception and robotic manipulation. However, a key challenge in the field is the lack of transferability between sensors due to design and manufacturing variations, which…

Dark wavefront sensing takes shape following quantum mechanics concepts in which one is able to "see" an object in one path of a two-arm interferometer using an as low as desired amount of light actually "hitting" the occulting object. A…

Recently, camera-controlled video generation has seen rapid development, offering more precise control over video generation. However, existing methods predominantly focus on camera control in perspective projection video generation, while…

Many adaptive optics systems operate by measuring the distortion of the wavefront in one wavelength range and performing the scientific observations in a second, different wavelength range. One common technique is to measure wavefront…

Enhancing visual odometry by exploiting sparse depth measurements from LiDAR is a promising solution for improving tracking accuracy of an odometry. Most existing works utilize a monocular pinhole camera, yet could suffer from poor…

Panoramic cameras, capable of capturing a 360-degree field of view, are crucial in robotic vision, particularly in environments with sparse features. However, non-upright panoramas due to unstable robot postures hinder downstream tasks.…

Physics-based differentiable rendering (PBDR) has become an efficient method in computer vision, graphics, and machine learning for addressing an array of inverse problems. PBDR allows patterns to be generated from perceptions which can be…