Article
Computer Science, Software Engineering
Fuyan Liu, Junwen Gan
Summary: In this paper, a novel approach for sampling indirect illumination using bidirectional path tracing and world space resampling reservoir is proposed. Light subpaths with high contribution are cached in a world space grid, allowing for sampling at any vertices along the eye path. Optimal samples are found by continuously updating the reservoirs stored in each cell based on resampling principles. Experimental results show that the algorithm achieves noticeable noise reduction in scenes lit by indirect light compared to path tracing, while maintaining interactive frame rates, albeit with additional time and memory consumption. In some special cases, the method even outperforms a plain bidirectional path tracer in terms of both image quality and performance.
COMPUTERS & GRAPHICS-UK
(2023)
Article
Optics
David Blinder, Maksymilian Chlipala, Tomasz Kozacki, Peter Schelkens
Summary: Computer-generated holography algorithms come in various forms, each with different trade-offs in visual quality and calculation speed. None of these algorithms can accurately capture all 3D visual cues simultaneously. A novel algorithm combining point-based CGH precision with ray-tracing accurate shading has been proposed.
Article
Computer Science, Software Engineering
Jie Guo, Zijing Zong, Yadong Song, Xihao Fu, Chengzhi Tao, Yanwen Guo, Ling-Qi Yan
Summary: This paper proposes a new method for probe-based global illumination (GI) rendering that can generate a wide range of GI effects, including glossy reflection with multiple bounces, in complex scenes. The method utilizes a gradient-based search algorithm and a neural image reconstruction method to achieve fast and high-quality GI rendering, while employing temporal reprojection and a temporal loss to improve temporal stability for animation sequences.
ACM TRANSACTIONS ON GRAPHICS
(2022)
Article
Computer Science, Information Systems
Qiwei Xing, Chunyi Chen, Zhihua Li
Summary: This study introduces a novel denoising algorithm framework that improves image quality through adaptive sampling and an improved bilateral filtering algorithm.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Software Engineering
Milan Jaros, Lubomir Riha, Petr Strakos, Matej Spetko
Summary: This study proposes a solution for path tracing of massive scenes on multiple GPUs, optimizing performance by analyzing memory access patterns and defining scene data distribution across CPUs. The approach is shown to be scalable and efficient, with only minor changes needed for application to other path tracers.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Multidisciplinary Sciences
Yanquan Mo, Fan Feng, Heng Mao, Junchao Fan, Liangyi Chen
Summary: Despite the wide application of structured illumination microscopy (SIM) in live-cell super-resolution imaging, aberrations caused by various sources remain a challenge. This study focused on investigating the impact of sample thickness on aberrations due to scattering of excitation light in SIM imaging, finding that thicker samples led to more severe aberrant interference light and degraded image reconstruction. The findings can guide future algorithm development to suppress SIM artefacts caused by scattering in thick samples.
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES
(2021)
Article
Plant Sciences
Shun-Ling Tan, Jia-Lin Huang, Feng-Ping Zhang, Shi-Bao Zhang, Wei Huang
Summary: This study revealed that low-light phases significantly affect the extent of PSI photoinhibition in fluctuating light conditions, with a higher light intensity inducing a higher proton gradient across thylakoid membranes. The activation of cyclic electron flow (CEF) is finely regulated to optimize the balance between photoprotection and light use efficiency in fluctuating light environments. Additionally, CEF activation in high-light phases is highly dependent on the PSI reduction state.
ENVIRONMENTAL AND EXPERIMENTAL BOTANY
(2021)
Article
Computer Science, Artificial Intelligence
Hongzhi Jiang, Yuxi Li, Huijie Zhao, Xudong Li, Xu Yang
Summary: Parallel single-pixel imaging (PSI) is a photography technique that captures light transport coefficients and enables 3D shape reconstruction under strong global illumination by extending single-pixel imaging (SI) to modern digital cameras. The local region extension (LRE) method is introduced to accelerate data acquisition of PSI, which is extremely beneficial for data acquisition efficiency. PSI possesses several properties and advantages, such as capturing complete light transport coefficients and not requiring special hardware or restrictions on the arrangement of projector-camera pairs.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Optics
Chen Fan, Hong Zhao, Zixin Zhao, Junxiang LI, Yijun DU, Xingyu Yang, Lu Zhang
Summary: We propose a novel single-shot quantitative phase imaging technique using a liquid crystal spatial light modulator (LC-SLM) under white light illumination. By studying the phase modulation characteristics of an LC-SLM under white light illumination, images captured at different wavelengths are equivalent to those captured at different defocus distances. The phase is retrieved from a single-shot color image using the transport of intensity equation. The proposed method shows flexibility and accuracy in quantitative phase imaging of various samples.
Article
Automation & Control Systems
Yizhi Wu, Fei Xie, Lei Huang, Rui Sun, Jiquan Yang, Qiang Yu
Summary: This paper proposes a path planning algorithm that does not require a prior global map. It combines convolutional evaluation and gradient first search methods to enable the robot to collect environmental information and perform path planning simultaneously, significantly improving the efficiency of path planning.
ROBOTICS AND AUTONOMOUS SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Faycal Abbas, Mehdi Malah, Mohamed Chaouki Babahenini
Summary: This paper proposes a method to approximate global illumination by calculating direct illumination, environmental light, and ambient occlusion. The method generates high-quality images without the need for additional computation in the 3D scene or screen space.
PATTERN RECOGNITION LETTERS
(2023)
Article
Computer Science, Software Engineering
Duan Gao, Haoyuan Mu, Kun Xu
Summary: We propose a novel method called neural global illumination for fast rendering of full global illumination in static scenes with dynamic viewpoint and area lighting. Our method utilizes a deep rendering network to model the mapping from each shading point to global illumination. We also introduce a neural-network-friendly input representation and a screen-space neural buffer to share global information between objects. This method can synthesize complex global illumination effects efficiently and is capable of handling scenes with multiple-bounce glossy interreflection, color bleeding, and caustics.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2023)
Article
Engineering, Electrical & Electronic
Praveen Kandula, Maitreya Suin, A. N. Rajagopalan
Summary: In this paper, an unsupervised low-light enhancement network using context-guided illumination-adaptive norm (CIN) is proposed. The network consists of two stages: the first stage uses a pixel amplifier module (PAM) to generate a coarse estimate, improving visibility and aesthetic quality, while the second stage enhances the image using CIN. A region-adaptive single input multiple output (SIMO) model is also introduced to generate multiple enhanced images for users to choose from. The experimental results show that the proposed model outperforms previous methods quantitatively and qualitatively.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Optics
Zhiqiang Fu, Qiang Geng, Jialong Chen, Li-An Chu, Ann-Shyn Chiang, Shih-Chi Chen
Summary: This study introduces a light sheet-based structured light illumination light field microscopy system for fast 3D imaging, utilizing a digital micromirror device to generate sinusoidal patterns rapidly. By combining deconvolution and HiLo algorithms, fast volumetric imaging with improved optical cross-sectioning capability is achieved. Imaging experiments on various samples show that this new method presents a fast 3D imaging solution with significantly enhanced optical cross-sectioning capability compared to standard light sheet-based LFM.
Article
Computer Science, Software Engineering
Y. Ouyang, S. Liu, M. Kettunen, M. Pharr, J. Pantaleoni
Summary: The paper introduces an effective path sampling algorithm for indirect lighting suitable for highly parallel GPU architectures, utilizing screen-space spatio-temporal resampling principles similar to ReSTIR to resample multi-bounce indirect lighting paths obtained from path tracing. By sharing important path information across time and pixels in the image, the resulting algorithm achieves a substantial error reduction compared to path tracing, leading to high-quality path traced global illumination at real-time frame rates on modern GPUs when combined with a denoiser.
COMPUTER GRAPHICS FORUM
(2021)
Article
Computer Science, Artificial Intelligence
Zhizhong Han, Mingyang Shang, Zhenbao Liu, Chi-Man Vong, Yu-Shen Liu, Matthias Zwicker, Junwei Han, C. L. Philip Chen
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2019)
Article
Computer Science, Software Engineering
Suiyun Zhang, Zhizhong Han, Yu-Kun Lai, Matthias Zwicker, Hui Zhang
Article
Computer Science, Software Engineering
Markus Kettunen, Erik Harkonen, Jaakko Lehtinen
ACM TRANSACTIONS ON GRAPHICS
(2019)
Article
Computer Science, Software Engineering
Quan Zheng, Matthias Zwicker
COMPUTER GRAPHICS FORUM
(2019)
Article
Computer Science, Software Engineering
Binh-Son Hua, Adrien Gruson, Victor Petitjean, Matthias Zwicker, Derek Nowrouzezahrai, Elmar Eisemann, Toshiya Hachisuka
COMPUTER GRAPHICS FORUM
(2019)
Article
Computer Science, Artificial Intelligence
Zhizhong Han, Honglei Lu, Zhenbao Liu, Chi-Man Vong, Yu-Shen Liu, Matthias Zwicker, Junwei Han, C. L. Philip Chen
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2019)
Article
Computer Science, Software Engineering
Suiyun Zhang, Zhizhong Han, Yu-Kun Lai, Matthias Zwicker, Hui Zhang
Summary: This article introduces an interactive framework based on active learning to help users create customized small object arrangements. By learning prior knowledge through probability mining and propagating user preferences using a novel active learning approach, the framework enables users to effectively create customized arrangements with minimal effort.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2021)
Article
Computer Science, Software Engineering
Markus Kettunen, Eugene D'Eon, Jacopo Pantaleoni, Jan Novak
Summary: This study provides an in-depth analysis of the sources of variance in state-of-the-art unbiased volumetric transmittance estimators, and proposes new methods for improving their efficiency. By utilizing novel statistical methods and density estimation techniques, the resulting estimator effectively reduces variance and improves accuracy, providing a universally optimal solution relative to prior work.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Software Engineering
Y. Ouyang, S. Liu, M. Kettunen, M. Pharr, J. Pantaleoni
Summary: The paper introduces an effective path sampling algorithm for indirect lighting suitable for highly parallel GPU architectures, utilizing screen-space spatio-temporal resampling principles similar to ReSTIR to resample multi-bounce indirect lighting paths obtained from path tracing. By sharing important path information across time and pixels in the image, the resulting algorithm achieves a substantial error reduction compared to path tracing, leading to high-quality path traced global illumination at real-time frame rates on modern GPUs when combined with a denoiser.
COMPUTER GRAPHICS FORUM
(2021)
Article
Computer Science, Software Engineering
Daqi Lin, Markus Kettunen, Benedikt Bitterli, Jacopo Pantaleoni, Cem Yuksel, Chris Wyman
Summary: As scenes become more complex and real-time applications embrace ray tracing, it is important to have path sampling algorithms that can maximize quality at low sample counts. This study introduces the theory of generalized resampled importance sampling (GRIS) to extend the existing theoretical foundation and derive variance bounds and convergence conditions in ReSTIR-based samplers. This not only guides practical algorithm design but also enables advanced path reuse between pixels.
ACM TRANSACTIONS ON GRAPHICS
(2022)
Article
Computer Science, Artificial Intelligence
Xinhai Liu, Zhizhong Han, Yu-Shen Liu, Matthias Zwicker
Summary: The researchers introduced a new fine-grained 3D shape dataset and proposed a novel method named FG3D-Net to address the issue of limited variance among subcategories in the same category. The method captures fine-grained local details of 3D shapes from multiple rendered views, outperforming other state-of-the-art methods in experiments under the fine-grained 3D shape dataset.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Proceedings Paper
Computer Science, Cybernetics
Yue Jiang, Wolfgang Stuerzlinger, Matthias Zwicker, Christof Lutteroth
PROCEEDINGS OF THE 2020 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS (CHI'20)
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Tao Hu, Zhizhong Han, Abhinav Shrivastava, Matthias Zwicker
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Qiyang Hu, Attila Szabo, Tiziano Portenier, Paolo Favaro, Matthias Zwicker
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Article
Computer Science, Artificial Intelligence
Zhizhong Han, Baorui Ma, Yu-Shen Liu, Matthias Zwicker
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)