中文
相关论文

相关论文: Non-Orthogonal Reduction for Rendering Fluorescent…

200 篇论文

Neural Radiance Field (NeRF) is a representation for 3D reconstruction from multi-view images. Despite some recent work showing preliminary success in editing a reconstructed NeRF with diffusion prior, they remain struggling to synthesize…

计算机视觉与模式识别 · 计算机科学 2024-11-14 Chieh Hubert Lin , Changil Kim , Jia-Bin Huang , Qinbo Li , Chih-Yao Ma , Johannes Kopf , Ming-Hsuan Yang , Hung-Yu Tseng

Image reconstruction under multiple light scattering is crucial in a number of applications such as diffraction tomography. The reconstruction problem is often formulated as a nonconvex optimization, where a nonlinear measurement model is…

计算机视觉与模式识别 · 计算机科学 2018-07-04 Yu Sun , Zhihao Xia , Ulugbek S. Kamilov

Learning neural radiance fields of a scene has recently allowed realistic novel view synthesis of the scene, but they are limited to synthesize images under the original fixed lighting condition. Therefore, they are not flexible for the…

计算机视觉与模式识别 · 计算机科学 2021-10-26 Quan Zheng , Gurprit Singh , Hans-Peter Seidel

We present a method that takes as input a set of images of a scene illuminated by unconstrained known lighting, and produces as output a 3D representation that can be rendered from novel viewpoints under arbitrary lighting conditions. Our…

计算机视觉与模式识别 · 计算机科学 2020-12-08 Pratul P. Srinivasan , Boyang Deng , Xiuming Zhang , Matthew Tancik , Ben Mildenhall , Jonathan T. Barron

Neural radiance fields (NeRFs) produce state-of-the-art view synthesis results. However, they are slow to render, requiring hundreds of network evaluations per pixel to approximate a volume rendering integral. Baking NeRFs into explicit…

计算机视觉与模式识别 · 计算机科学 2022-05-11 Benjamin Attal , Jia-Bin Huang , Michael Zollhoefer , Johannes Kopf , Changil Kim

We present a suite of techniques for jointly optimizing triangle meshes and shading models to match the appearance of reference scenes. This capability has a number of uses, including appearance-preserving simplification of extremely…

图形学 · 计算机科学 2021-04-12 Jon Hasselgren , Jacob Munkberg , Jaakko Lehtinen , Miika Aittala , Samuli Laine

Neural Radiance Fields (NeRF) is a popular view synthesis technique that represents a scene as a continuous volumetric function, parameterized by multilayer perceptrons that provide the volume density and view-dependent emitted radiance at…

计算机视觉与模式识别 · 计算机科学 2021-12-08 Dor Verbin , Peter Hedman , Ben Mildenhall , Todd Zickler , Jonathan T. Barron , Pratul P. Srinivasan

Incremental scene reconstruction is essential to the navigation in robotics. Most of the conventional methods typically make use of either TSDF (truncated signed distance functions) volume or neural networks to implicitly represent the…

机器人学 · 计算机科学 2024-04-30 Shaofan Liu , Junbo Chen , Jianke Zhu

In this paper, we propose a novel projector-camera system for practical and low-cost acquisition of a dense object 3D model with the spectral reflectance property. In our system, we use a standard RGB camera and leverage an off-the-shelf…

计算机视觉与模式识别 · 计算机科学 2019-08-23 Chunyu Li , Yusuke Monno , Hironori Hidaka , Masatoshi Okutomi

We present a novel convolutional neural network architecture for photometric stereo (Woodham, 1980), a problem of recovering 3D object surface normals from multiple images observed under varying illuminations. Despite its long history in…

计算机视觉与模式识别 · 计算机科学 2018-05-30 Tatsunori Taniai , Takanori Maehara

Due to the real-time rendering performance, 3D Gaussian Splatting (3DGS) has emerged as the leading method for radiance field reconstruction. However, its reliance on spherical harmonics for color encoding inherently limits its ability to…

计算机视觉与模式识别 · 计算机科学 2026-02-24 Yixin Yang , Bojian Wu , Yang Zhou , Hui Huang

We present a novel Relightable Neural Renderer (RNR) for simultaneous view synthesis and relighting using multi-view image inputs. Existing neural rendering (NR) does not explicitly model the physical rendering process and hence has limited…

计算机视觉与模式识别 · 计算机科学 2020-06-16 Zhang Chen , Anpei Chen , Guli Zhang , Chengyuan Wang , Yu Ji , Kiriakos N. Kutulakos , Jingyi Yu

In previous work, it was shown that a camera can theoretically be made more colorimetric - its RGBs become more linearly related to XYZ tristimuli - by placing a specially designed color filter in the optical path. While the prior art…

图像与视频处理 · 电气工程与系统科学 2022-01-28 Yuteng Zhu , Graham D. Finlayson

This paper introduces a novel framework for image quality transfer based on conditional flow matching (CFM). Unlike conventional generative models that rely on iterative sampling or adversarial objectives, CFM learns a continuous flow…

计算机视觉与模式识别 · 计算机科学 2025-10-15 Huu Tien Nguyen , Ahmed Karam Eldaly

Vision in adverse weather conditions, whether it be snow, rain, or fog is challenging. In these scenarios, scattering and attenuation severly degrades image quality. Handling such inclement weather conditions, however, is essential to…

计算机视觉与模式识别 · 计算机科学 2023-05-04 Andrea Ramazzina , Mario Bijelic , Stefanie Walz , Alessandro Sanvito , Dominik Scheuble , Felix Heide

We present SpectralUnmix, an R package for regularized non-negative matrix factorization (NMF), implemented in torch with optional GPU acceleration. The package estimates low-rank non-negative representations through proximal-gradient…

天体物理仪器与方法 · 物理学 2026-04-06 Rafael S. de Souza , Paula Coelho , Niranjana P , Ana L. Chies-Santos , Rogério Riffel

Achieving high-quality High Dynamic Range (HDR) imaging on resource-constrained edge devices is a critical challenge in computer vision, as its performance directly impacts downstream tasks such as intelligent surveillance and autonomous…

计算机视觉与模式识别 · 计算机科学 2025-09-25 Yu-Shen Huang , Tzu-Han Chen , Cheng-Yen Hsiao , Shaou-Gang Miaou

Reconstruction of deformable scenes from endoscopic videos is important for many applications such as intraoperative navigation, surgical visual perception, and robotic surgery. It is a foundational requirement for realizing autonomous…

计算机视觉与模式识别 · 计算机科学 2025-03-19 Shreya Saha , Zekai Liang , Shan Lin , Jingpei Lu , Michael Yip , Sainan Liu

Most image deblurring methods assume an over-simplistic image formation model and as a result are sensitive to more realistic image degradations. We propose a novel variational framework, that explicitly handles pixel saturation, noise,…

计算机视觉与模式识别 · 计算机科学 2018-06-05 Jérémy Anger , Mauricio Delbracio , Gabriele Facciolo

On-invasive optical imaging techniques are essential diagnostic tools in many fields. Although various recent methods have been proposed to utilize and control light in multiple scattering media, non-invasive optical imaging through and…