相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Software Engineering
A. Tewari et al.
Summary: Synthesizing photo-realistic images and videos is a key focus in computer graphics research. Neural rendering combines classical computer graphics techniques with machine learning to create algorithms for synthesizing images from real-world observations. This field has seen significant progress in recent years, with methods that can handle static scenes as well as non-rigidly deforming objects, scene editing, and composition. These methods have the advantage of being 3D-consistent and can be used for generative tasks. This report provides a comprehensive overview of state-of-the-art neural rendering methods, fundamental concepts, and open challenges.
COMPUTER GRAPHICS FORUM
(2022)
Article
Computer Science, Software Engineering
Zhengfei Kuang et al.
Summary: This study presents a novel method to acquire object representations from online image collections, capturing high-quality geometry and material properties. By using a multi-stage approach, the surface geometry and camera parameters are inferred, and the training efficiency is improved by leveraging coarse foreground object masks. A robust normal estimation technique is employed to eliminate geometric noise while retaining crucial details. The resulting object acquisition framework is highly modular and efficient, and is advantageous in capturing high-quality geometry and appearance properties useful for rendering applications.
ACM TRANSACTIONS ON GRAPHICS
(2022)
Article
Computer Science, Software Engineering
Fuqiang Zhao et al.
Summary: In this paper, a comprehensive neural approach for high-quality reconstruction, compression, and rendering of human performances from dense multi-view videos is presented. The approach combines traditional animated mesh workflow with efficient neural techniques to generate high-quality surfaces and animated meshes. Various rendering schemes are discussed to achieve flexible rendering under different bandwidth settings.
ACM TRANSACTIONS ON GRAPHICS
(2022)
Article
Computer Science, Software Engineering
Georgios Kopanas et al.
Summary: This paper addresses the challenges of view-dependent effects, such as reflections, for image-based and neural rendering algorithms. The authors propose a new point-based representation to compute Neural Point Catacaustics, enabling the synthesis of novel views with curved reflectors. Their approach leverages a neural warp field to model catacaustic trajectories of reflections, allowing efficient rendering of complex specular effects.
ACM TRANSACTIONS ON GRAPHICS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yao Yao et al.
Summary: We propose a differentiable rendering framework for material and lighting estimation from multi-view images and reconstructed geometry. Our framework can model illuminations of any static scenes and handle complex lightings and geometries. By introducing smoothness regularization and Lambertian assumption during optimization, our method outperforms previous approaches in terms of rendering quality.
COMPUTER VISION, ECCV 2022, PT XXXI
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhaoxi Chen et al.
Summary: In this work, we propose a principled framework called Relighting4D that enables free-viewpoints relighting of human body under unknown illuminations. By decomposing the spacetime varying geometry and reflectance into neural fields and integrating them into reflectance-aware physically based rendering, our framework can effectively relight dynamic human actors with free-viewpoints.
COMPUTER VISION - ECCV 2022, PT XIV
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Viktor Rudnev et al.
Summary: NeRF-OSR is the first approach for outdoor scene relighting based on neural radiance fields, allowing simultaneous editing of illumination and camera viewpoint. By manipulating a collection of outdoor photos, it enables direct control over scene illumination and maintains scene realism.
COMPUTER VISION - ECCV 2022, PT XVI
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Eldar Insafutdinov et al.
Summary: This study presents a method for accurately reconstructing partly-symmetric objects, leveraging structural priors to complete missing information. The method achieves high fidelity reconstruction and rendering capabilities.
COMPUTER VISION - ECCV 2022, PT XXXII
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Felix Wimbauer et al.
Summary: This paper presents a weakly supervised method that can decompose a single image of an object into shape, material, and global lighting parameters. The method successfully de-renders 2D images into decomposed 3D representations and generalizes to unseen object categories. Additionally, a photo-realistic synthetic test set is introduced for quantitative evaluation.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yuanqing Zhang et al.
Summary: This paper proposes a novel approach for efficiently recovering spatially-varying indirect illumination and demonstrates its superior performance compared to previous methods in synthesizing realistic renderings under novel viewpoints and illumination.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Dor Verbin et al.
Summary: NeRF excels at representing fine geometric structures with smoothly varying view-dependent appearance, but often fails to accurately capture and reproduce the appearance of glossy surfaces. Ref-NeRF addresses this limitation by introducing a representation of reflected radiance and structuring this function using a collection of spatially-varying scene properties, significantly improving the realism and accuracy of specular reflections when combined with a regularizer on normal vectors.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Haoyu Guo et al.
Summary: This paper addresses the challenge of reconstructing 3D indoor scenes from multi-view images and proposes a method that incorporates planar constraints into the implicit neural representation-based reconstruction. The method outperforms previous ones in terms of 3D reconstruction quality.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Jacob Munkberg et al.
Summary: This paper presents an efficient method for jointly optimizing topology, materials and lighting from multi-view image observations. The proposed approach outputs triangle meshes with spatially-varying materials and environment lighting that can be used in any traditional graphics engine. By leveraging recent advancements in differentiable rendering and differentiable marching tetrahedrons, the authors enable gradient-based optimization directly on the surface mesh and efficiently recover all-frequency lighting.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Jonathan T. Barron et al.
Summary: Researchers propose a model called mip-NeRF 360 that uses non-linear scene parameterization, online distillation, and distortion-based regularization to address the challenges posed by unbounded scenes. Compared to existing models, it performs better in view synthesis and depth map generation, and is able to handle highly intricate unbounded real-world scenes.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Francois Darmon et al.
Summary: The paper proposes a method called NeuralWarp to improve the accuracy of neural implicit surface reconstruction by adding a direct photo-consistency term across different views. The approach optimizes the implicit geometry to achieve consistent view warping using predicted occupancy and normals, and measures their similarity using robust structural similarity. It also handles visibility and occlusion to encourage a complete reconstruction. Experimental results demonstrate that NeuralWarp outperforms state-of-the-art unsupervised implicit surface reconstructions by over 20% on standard benchmarks.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Software Engineering
Julien Philip et al.
Summary: The neural relighting algorithm introduced in this study enables interactive free-viewpoint navigation in captured indoors scenes, allowing synthetic changes in illumination while maintaining coherent rendering of shadows and glossy materials. By utilizing both image-based and physically based rendering elements, along with a three-dimensional mesh obtained through multiview stereo reconstruction, the method facilitates learning of an implicit representation of scene materials and illumination.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Software Engineering
Xiuming Zhang et al.
Summary: This study addresses the problem of recovering the shape and reflectance of objects from multi-view images under unknown lighting conditions. They propose the NeRFactor method, which can recover 3D neural fields of surface normals, light visibility, albedo, and BRDF, and outperforms existing techniques across various tasks.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Mark Boss et al.
Summary: Decomposing a scene into its shape, reflectance, and illumination is a challenging problem, especially when dealing with unconstrained environmental illumination. Our proposed NeRD technique utilizes physically-based rendering to decompose the scene into spatially varying BRDF material properties, enabling fast real-time rendering with novel illuminations.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Kai Zhang et al.
Summary: PhySG is an end-to-end inverse rendering pipeline that reconstructs geometry, materials, and illumination from images. It uses mixtures of spherical Gaussians and MLPs to represent specular BRDFs and geometry. The method is shown to work on scenes with challenging reflectance characteristics.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Ziang Cheng et al.
Summary: This paper proposes a simple and practical solution to overcome the challenge of establishing cross-view correspondences in multi-view reconstruction using a co-located camera-light scanner device. By formulating the reconstruction task as a joint energy minimization over surface geometry and reflectance, the authors are able to robustly recover globally optimal shape and reflectance from a small number of input views. Extensive experiments on simulated and real data validate the method and discuss possible future extensions.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yang Liu et al.
Summary: In this study, a self-supervised method for image relighting of single view images in the wild is proposed. The method utilizes an auto-encoder to deconstruct images into illumination and content encodings, introducing a novel spherical harmonic loss for estimating scene illumination. Experimental results show that the method can realistically re-light input images without supervision, achieving similar performance to supervised methods while avoiding common lighting artifacts.
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021)
(2021)
Article
Computer Science, Software Engineering
A. Tewari et al.
COMPUTER GRAPHICS FORUM
(2020)
Article
Computer Science, Software Engineering
Yu Guo et al.
ACM TRANSACTIONS ON GRAPHICS
(2020)
Article
Computer Science, Software Engineering
Duan Gao et al.
ACM TRANSACTIONS ON GRAPHICS
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Thomas Nestmeyer et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Carolin Schmitt et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Jiayu Yang et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Computer Science, Software Engineering
Simon Rodriguez et al.
PROCEEDINGS OF THE ACM ON COMPUTER GRAPHICS AND INTERACTIVE TECHNIQUES
(2020)
Article
Computer Science, Software Engineering
Duan Gao et al.
ACM TRANSACTIONS ON GRAPHICS
(2019)
Article
Computer Science, Software Engineering
Julien Philip et al.
ACM TRANSACTIONS ON GRAPHICS
(2019)
Article
Computer Science, Software Engineering
Merlin Nimier-David et al.
ACM TRANSACTIONS ON GRAPHICS
(2019)
Article
Computer Science, Software Engineering
Thomas Whelan et al.
ACM TRANSACTIONS ON GRAPHICS
(2018)
Article
Computer Science, Software Engineering
Giljoo Nam et al.
ACM TRANSACTIONS ON GRAPHICS
(2018)
Proceedings Paper
Computer Science, Theory & Methods
Zhengqin Li et al.
SIGGRAPH ASIA'18: SIGGRAPH ASIA 2018 TECHNICAL PAPERS
(2018)
Article
Computer Science, Software Engineering
Zhengqin Li et al.
ACM TRANSACTIONS ON GRAPHICS
(2018)
Proceedings Paper
Computer Science, Theory & Methods
Giljoo Nam et al.
SIGGRAPH ASIA'18: SIGGRAPH ASIA 2018 TECHNICAL PAPERS
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Kai Han et al.
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2016)
Article
Computer Science, Artificial Intelligence
Jonathan T. Barron et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2015)
Proceedings Paper
Computer Science, Artificial Intelligence
Clement Godard et al.
2015 INTERNATIONAL CONFERENCE ON 3D VISION
(2015)
Article
Computer Science, Software Engineering
Yichang Shih et al.
ACM TRANSACTIONS ON GRAPHICS
(2013)
Article
Computer Science, Artificial Intelligence
Asmaa Hosni et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2013)
Article
Robotics
A. Geiger et al.
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
(2013)
Article
Computer Science, Software Engineering
Sudipta N. Sinha et al.
ACM TRANSACTIONS ON GRAPHICS
(2012)
Article
Computer Science, Artificial Intelligence
Yasutaka Furukawa et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2010)
Article
Computer Science, Artificial Intelligence
Z Wang et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2004)
Article
Computer Science, Artificial Intelligence
D Scharstein et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2002)
