Computer Graphics Forum最新文献_第10页

VMF Diffuse: A unified rough diffuse BRDF VMF 漫反射：统一的粗糙漫反射 BRDF

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-07-24 DOI: 10.1111/cgf.15149

Eugene d'Eon, Andrea Weidlich

引用次数: 0

A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis 利用多重照明合成进行辐射场再照明的扩散方法

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-07-24 DOI: 10.1111/cgf.15147

Y. Poirier-Ginter, A. Gauthier, J. Phillip, J.-F. Lalonde, G. Drettakis

{"title":"A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis","authors":"Y. Poirier-Ginter, A. Gauthier, J. Phillip, J.-F. Lalonde, G. Drettakis","doi":"10.1111/cgf.15147","DOIUrl":"10.1111/cgf.15147","url":null,"abstract":"Relighting radiance fields is severely underconstrained for multi-view data, which is most often captured under a single illumination condition; It is especially hard for full scenes containing multiple objects. We introduce a method to create relightable radiance fields using such single-illumination data by exploiting priors extracted from 2D image diffusion models. We first fine-tune a 2D diffusion model on a multi-illumination dataset conditioned by light direction, allowing us to augment a single-illumination capture into a realistic – but possibly inconsistent – multi-illumination dataset from directly defined light directions. We use this augmented data to create a relightable radiance field represented by 3D Gaussian splats. To allow direct control of light direction for low-frequency lighting, we represent appearance with a multi-layer perceptron parameterized on light direction. To enforce multi-view consistency and overcome inaccuracies we optimize a per-image auxiliary feature vector. We show results on synthetic and real multi-view data under single illumination, demonstrating that our method successfully exploits 2D diffusion model priors to allow realistic 3D relighting for complete scenes.","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"43 4","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141779327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Realistic Facial Age Transformation with 3D Uplifting 通过 3D 提升技术实现逼真的面部年龄变化

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-07-24 DOI: 10.1111/cgf.15146

X. Li, G. C. Guarnera, A. Lin, A. Ghosh

引用次数: 0

Bridge Sampling for Connections via Multiple Scattering Events 通过多个散射事件进行连接的桥接采样

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-07-24 DOI: 10.1111/cgf.15160

Vincent Schüßler, Johannes Hanika, Carsten Dachsbacher

{"title":"Bridge Sampling for Connections via Multiple Scattering Events","authors":"Vincent Schüßler, Johannes Hanika, Carsten Dachsbacher","doi":"10.1111/cgf.15160","DOIUrl":"10.1111/cgf.15160","url":null,"abstract":"<div>\u0000 Explicit sampling of and connecting to light sources is often essential for reducing variance in Monte Carlo rendering. In dense, forward-scattering participating media, its benefit declines, as significant transport happens over longer multiple-scattering paths around the straight connection to the light. Sampling these paths is challenging, as their contribution is shaped by the product of reciprocal squared distance terms and the phase functions. Previous work demonstrates that sampling several of these terms jointly is crucial. However, these methods are tied to low-order scattering or struggle with highly-peaked phase functions.\u0000 We present a method for sampling a bridge: a subpath of arbitrary vertex count connecting two vertices. Its probability density is proportional to all phase functions at inner vertices and reciprocal squared distance terms. To achieve this, we importance sample the phase functions first, and subsequently all distances at once. For the latter, we sample an independent, preliminary distance for each edge of the bridge, and afterwards scale the bridge such that it matches the connection distance. The scale factor can be marginalized out analytically to obtain the probability density of the bridge. This approach leads to a simple algorithm and can construct bridges of any vertex count. For the case of one or two inserted vertices, we also show an alternative without scaling or marginalization.\u0000 For practical path sampling, we present a method to sample the number of bridge vertices whose distribution depends on the connection distance, the phase function, and the collision coefficient. While our importance sampling treats media as homogeneous we demonstrate its effectiveness on heterogeneous media.\u0000 </div>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"43 4","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.15160","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141785867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Stereo-consistent Screen Space Reflection 立体一致的屏幕空间反射

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-07-24 DOI: 10.1111/cgf.15159

X. Wu, Y. Xu, L. Wang

引用次数: 0

Neural SSS: Lightweight Object Appearance Representation 神经 SSS：轻量级物体外观表示法

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-07-24 DOI: 10.1111/cgf.15158

T. TG, D. M. Tran, H. W. Jensen, R. Ramamoorthi, J. R. Frisvad

引用次数: 0

Patch Decomposition for Efficient Mesh Contours Extraction 高效提取网格轮廓的补丁分解法

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-07-24 DOI: 10.1111/cgf.15154

P. Tsiapkolis, P. Bénard

引用次数: 0

Non-Orthogonal Reduction for Rendering Fluorescent Materials in Non-Spectral Engines 在非光谱引擎中渲染荧光材料的非正交还原法

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-07-24 DOI: 10.1111/cgf.15150

A. Fichet, L. Belcour, P. Barla

引用次数: 0

Scaling Painting Style Transfer 缩放绘画风格转移

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-07-24 DOI: 10.1111/cgf.15155

Bruno Galerne, Lara Raad, José Lezama, Jean-Michel Morel

{"title":"Scaling Painting Style Transfer","authors":"Bruno Galerne, Lara Raad, José Lezama, Jean-Michel Morel","doi":"10.1111/cgf.15155","DOIUrl":"10.1111/cgf.15155","url":null,"abstract":"Neural style transfer (NST) is a deep learning technique that produces an unprecedentedly rich style transfer from a style image to a content image. It is particularly impressive when it comes to transferring style from a painting to an image. NST was originally achieved by solving an optimization problem to match the global statistics of the style image while preserving the local geometric features of the content image. The two main drawbacks of this original approach is that it is computationally expensive and that the resolution of the output images is limited by high GPU memory requirements. Many solutions have been proposed to both accelerate NST and produce images with larger size. However, our investigation shows that these accelerated methods all compromise the quality of the produced images in the context of painting style transfer. Indeed, transferring the style of a painting is a complex task involving features at different scales, from the color palette and compositional style to the fine brushstrokes and texture of the canvas. This paper provides a solution to solve the original global optimization for ultra-high resolution (UHR) images, enabling multiscale NST at unprecedented image sizes. This is achieved by spatially localizing the computation of each forward and backward passes through the VGG network. Extensive qualitative and quantitative comparisons, as well as a perceptual study, show that our method produces style transfer of unmatched quality for such high-resolution painting styles. By a careful comparison, we show that state-of-the-art fast methods are still prone to artifacts, thus suggesting that fast painting style transfer remains an open problem.","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"43 4","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141779333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Neural Histogram-Based Glint Rendering of Surfaces With Spatially Varying Roughness 基于神经直方图的空间粗糙度变化表面闪光渲染

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-07-24 DOI: 10.1111/cgf.15157

I. Shah, L. E. Gamboa, A. Gruson, P. J. Narayanan

引用次数: 0