English
Related papers

Related papers: Towards Monocular Shape from Refraction

200 papers

Robust face reconstruction from monocular image in general lighting conditions is challenging. Methods combining deep neural network encoders with differentiable rendering have opened up the path for very fast monocular reconstruction of…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Abdallah Dib , Cedric Thebault , Junghyun Ahn , Philippe-Henri Gosselin , Christian Theobalt , Louis Chevallier

Unlike opaque object, novel view synthesis of transparent object is a challenging task, because transparent object refracts light of background causing visual distortions on the transparent object surface along the viewpoint change.…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Heechan Yoon , Seungkyu Lee

The reconstruction of dense 3D models of face geometry and appearance from a single image is highly challenging and ill-posed. To constrain the problem, many approaches rely on strong priors, such as parametric face models learned from…

Computer Vision and Pattern Recognition · Computer Science 2018-04-02 Ayush Tewari , Michael Zollhöfer , Pablo Garrido , Florian Bernard , Hyeongwoo Kim , Patrick Pérez , Christian Theobalt

A general algorithm for calculating the reflection and refraction of nonuniform plane waves from an arbitrarily oriented and charged planar interface between two lossy isotropic media is proposed based on the decomposition of the complex…

Optics · Physics 2026-02-24 Zhili Lin

In this work, we propose a novel method for the detailed reconstruction of transparent objects by exploiting polarimetric cues. Most of the existing methods usually lack sufficient constraints and suffer from the over-smooth problem. Hence,…

Computer Vision and Pattern Recognition · Computer Science 2022-08-26 Mingqi Shao , Chongkun Xia , Dongxu Duan , Xueqian Wang

Accurate reconstruction of both the geometric and topological details of a 3D object from a single 2D image embodies a fundamental challenge in computer vision. Existing explicit/implicit solutions to this problem struggle to recover…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Mohammad Samiul Arshad , William J. Beksi

Imaging is of great importance in everyday life and various fields of science and technology. Conventional imaging is achieved by bending light rays originating from an object with a lens. Such ray bending requires space-variant structures,…

Optics · Physics 2023-10-02 Wenzhe Liu , Jingguang Chen , Tongyu Li , Zhe Zhang , Fang Guan , Lei Shi , Jian Zi , C. T. Chan

Joint camera pose and dense geometry estimation from a set of images or a monocular video remains a challenging problem due to its computational complexity and inherent visual ambiguities. Most dense incremental reconstruction systems…

Computer Vision and Pattern Recognition · Computer Science 2024-04-18 Kirill Mazur , Gwangbin Bae , Andrew J. Davison

We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstruction to establish geometric constraints on pixels in the video.…

Computer Vision and Pattern Recognition · Computer Science 2020-08-28 Xuan Luo , Jia-Bin Huang , Richard Szeliski , Kevin Matzen , Johannes Kopf

In this article, a new method for segmentation and restoration of images on two-dimensional surfaces is given. Active contour models for image segmentation are extended to images on surfaces. The evolving curves on the surfaces are…

Computer Vision and Pattern Recognition · Computer Science 2015-05-04 Heike Benninghoff , Harald Garcke

It has been recently proven that natural images exhibit scaling properties analogue to those of turbulent flows. These properties allow regarding each image as a multifractal object, for which its most singular manifold conveys the most of…

Statistical Mechanics · Physics 2007-05-23 Antonio Turiel , Angela del Pozo

Reconstructing an object's geometry and appearance from multiple images, also known as inverse rendering, is a fundamental problem in computer graphics and vision. Inverse rendering is inherently ill-posed because the captured image is an…

Computer Vision and Pattern Recognition · Computer Science 2022-03-28 Akshat Dave , Yongyi Zhao , Ashok Veeraraghavan

Optics naturally provides us with some powerful mathematical operations. Here we experimentally demonstrate that during reflection or refraction at a single optical planar interface, the optical computing of spatial differentiation can be…

We analyze multi-bounce propagation of light in an unknown hidden volume and demonstrate that the reflected light contains sufficient information to recover the 3D structure of the hidden scene. We formulate the forward and inverse theory…

We present a fast and simple technique to convert images into a radiance surface-based scene representation. Building on existing radiance volume reconstruction algorithms, we introduce a subtle yet impactful modification of the loss…

A high-accuracy solution of the diffraction problem has become necessary for the treatment of certain special questions of statistical physics. This article reports the creation of a computer program that serves as an instrumental method of…

Optics · Physics 2013-08-30 Vladimir V. Savukov , Igor V. Golubenko

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…

Computer Vision and Pattern Recognition · Computer Science 2019-08-21 Roman Klokov , Jakob Verbeek , Edmond Boyer

Neural Radiance Fields (NeRF) have demonstrated exceptional capabilities in reconstructing complex scenes with high fidelity. However, NeRF's view dependency can only handle low-frequency reflections. It falls short when handling complex…

Computer Vision and Pattern Recognition · Computer Science 2024-11-08 Chen Gao , Yipeng Wang , Changil Kim , Jia-Bin Huang , Johannes Kopf

Continuous-domain visual signals are usually captured as discrete (digital) images. This operation is not invertible in general, in the sense that the continuous-domain signal cannot be exactly reconstructed based on the discrete image,…

Information Theory · Computer Science 2016-01-20 Mitra Fatemi , Arash Amini , Loic Baboulaz , Martin Vetterli

Recent 3D face reconstruction methods have made remarkable advancements, yet there remain huge challenges in monocular high-quality facial reflectance reconstruction. Existing methods rely on a large amount of light-stage captured data to…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Xingyu Ren , Jiankang Deng , Yuhao Cheng , Jia Guo , Chao Ma , Yichao Yan , Wenhan Zhu , Xiaokang Yang