Computer Graphics Forum最新文献_第9页

PCLC-Net: Point Cloud Completion in Arbitrary Poses with Learnable Canonical Space PCLC-Net：利用可学习的典型空间完成任意姿态的点云补全

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-10-24 DOI: 10.1111/cgf.15217

Hanmo Xu, Qingyao Shuai, Xuejin Chen

{"title":"PCLC-Net: Point Cloud Completion in Arbitrary Poses with Learnable Canonical Space","authors":"Hanmo Xu, Qingyao Shuai, Xuejin Chen","doi":"10.1111/cgf.15217","DOIUrl":"https://doi.org/10.1111/cgf.15217","url":null,"abstract":"<p>Recovering the complete structure from partial point clouds in arbitrary poses is challenging. Recently, many efforts have been made to address this problem by developing SO(3)-equivariant completion networks or aligning the partial point clouds with a predefined canonical space before completion. However, these approaches are limited to random rotations only or demand costly pose annotation for model training. In this paper, we present a novel Network for Point cloud Completion with Learnable Canonical space (PCLC-Net) to reduce the need for pose annotations and extract SE(3)-invariant geometry features to improve the completion quality in arbitrary poses. Without pose annotations, our PCLC-Net utilizes self-supervised pose estimation to align the input partial point clouds to a canonical space that is learnable for an object category and subsequently performs shape completion in the learned canonical space. Our PCLC-Net can complete partial point clouds with arbitrary SE(3) poses without requiring pose annotations for supervision. Our PCLC-Net achieves state-of-the-art results on shape completion with arbitrary SE(3) poses on both synthetic and real scanned data. To the best of our knowledge, our method is the first to achieve shape completion in arbitrary poses without pose annotations during network training.</p>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"43 7","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142665129","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

Gaussian in the Dark: Real-Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting 黑暗中的高斯：利用高斯拼接技术从不连贯的黑暗图像中实时合成视图

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-10-24 DOI: 10.1111/cgf.15213

Sheng Ye, Zhen-Hui Dong, Yubin Hu, Yu-Hui Wen, Yong-Jin Liu

{"title":"Gaussian in the Dark: Real-Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting","authors":"Sheng Ye, Zhen-Hui Dong, Yubin Hu, Yu-Hui Wen, Yong-Jin Liu","doi":"10.1111/cgf.15213","DOIUrl":"https://doi.org/10.1111/cgf.15213","url":null,"abstract":"<p>3D Gaussian Splatting has recently emerged as a powerful representation that can synthesize remarkable novel views using consistent multi-view images as input. However, we notice that images captured in dark environments where the scenes are not fully illuminated can exhibit considerable brightness variations and multi-view inconsistency, which poses great challenges to 3D Gaussian Splatting and severely degrades its performance. To tackle this problem, we propose Gaussian-DK. Observing that inconsistencies are mainly caused by camera imaging, we represent a consistent radiance field of the physical world using a set of anisotropic 3D Gaussians, and design a camera response module to compensate for multi-view inconsistencies. We also introduce a step-based gradient scaling strategy to constrain Gaussians near the camera, which turn out to be floaters, from splitting and cloning. Experiments on our proposed benchmark dataset demonstrate that Gaussian-DK produces high-quality renderings without ghosting and floater artifacts and significantly outperforms existing methods. Furthermore, we can also synthesize light-up images by controlling exposure levels that clearly show details in shadow areas.</p>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"43 7","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142665189","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

Efficient Environment Map Rendering Based on Decomposition

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-10-22 DOI: 10.1111/cgf.15264

Yu-Ting Wu

{"title":"Efficient Environment Map Rendering Based on Decomposition","authors":"Yu-Ting Wu","doi":"10.1111/cgf.15264","DOIUrl":"https://doi.org/10.1111/cgf.15264","url":null,"abstract":"<p>This paper presents an efficient environment map sampling algorithm designed to render high-quality, low-noise images with only a few light samples, making it ideal for real-time applications. We observe that bright pixels in the environment map produce high-frequency shading effects, such as sharp shadows and shading, while the rest influence the overall tone of the scene. Building on this insight, our approach differs from existing techniques by categorizing the pixels in an environment map into emissive and non-emissive regions and developing specialized algorithms tailored to the distinct properties of each region. By decomposing the environment lighting, we ensure that light sources are deposited on bright pixels, leading to more accurate shadows and specular highlights. Additionally, this strategy allows us to exploit the smoothness in the low-frequency component by rendering a smaller image with more lights, thereby enhancing shading accuracy. Extensive experiments demonstrate that our method significantly reduces shadow artefacts and image noise compared to previous techniques, while also achieving lower numerical errors across a range of illumination types, particularly under limited sample conditions.</p>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143513565","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

TempDiff: Enhancing Temporal-awareness in Latent Diffusion for Real-World Video Super-Resolution TempDiff：增强潜在扩散中的时间感知，实现真实世界的视频超分辨率

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-10-18 DOI: 10.1111/cgf.15211

Q. Jiang, Q.L. Wang, L.H. Chi, X.H. Chen, Q.Y. Zhang, R. Zhou, Z.Q. Deng, J.S. Deng, B.B. Tang, S.H. Lv, J. Liu

{"title":"TempDiff: Enhancing Temporal-awareness in Latent Diffusion for Real-World Video Super-Resolution","authors":"Q. Jiang, Q.L. Wang, L.H. Chi, X.H. Chen, Q.Y. Zhang, R. Zhou, Z.Q. Deng, J.S. Deng, B.B. Tang, S.H. Lv, J. Liu","doi":"10.1111/cgf.15211","DOIUrl":"https://doi.org/10.1111/cgf.15211","url":null,"abstract":"<p>Latent diffusion models (LDMs) have demonstrated remarkable success in generative modeling. It is promising to leverage the potential of diffusion priors to enhance performance in image and video tasks. However, applying LDMs to video super-resolution (VSR) presents significant challenges due to the high demands for realistic details and temporal consistency in generated videos, exacerbated by the inherent stochasticity in the diffusion process. In this work, we propose a novel diffusion-based framework, Temporal-awareness Latent Diffusion Model (TempDiff), specifically designed for real-world video super-resolution, where degradations are diverse and complex. TempDiff harnesses the powerful generative prior of a pre-trained diffusion model and enhances temporal awareness through the following mechanisms: 1) Incorporating temporal layers into the denoising U-Net and VAE-Decoder, and fine-tuning these added modules to maintain temporal coherency; 2) Estimating optical flow guidance using a pre-trained flow net for latent optimization and propagation across video sequences, ensuring overall stability in the generated high-quality video. Extensive experiments demonstrate that TempDiff achieves compelling results, outperforming state-of-the-art methods on both synthetic and real-world VSR benchmark datasets. Code will be available at https://github.com/jiangqin567/TempDiff</p>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"43 7","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142665051","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

NeuPreSS: Compact Neural Precomputed Subsurface Scattering for Distant Lighting of Heterogeneous Translucent Objects NeuPreSS：用于异质半透明物体远距离照明的紧凑型神经预计算次表面散射法

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-10-18 DOI: 10.1111/cgf.15234

T. TG, J. R. Frisvad, R. Ramamoorthi, H. W. Jensen

{"title":"NeuPreSS: Compact Neural Precomputed Subsurface Scattering for Distant Lighting of Heterogeneous Translucent Objects","authors":"T. TG, J. R. Frisvad, R. Ramamoorthi, H. W. Jensen","doi":"10.1111/cgf.15234","DOIUrl":"https://doi.org/10.1111/cgf.15234","url":null,"abstract":"<div>\u0000 <p>Monte Carlo rendering of translucent objects with heterogeneous scattering properties is often expensive both in terms of memory and computation. If the scattering properties are described by a 3D texture, memory consumption is high. If we do path tracing and use a high dynamic range lighting environment, the computational cost of the rendering can easily become significant. We propose a compact and efficient neural method for representing and rendering the appearance of heterogeneous translucent objects. Instead of assuming only surface variation of optical properties, our method represents the appearance of a full object taking its geometry and volumetric heterogeneities into account. This is similar to a neural radiance field, but our representation works for an arbitrary distant lighting environment. In a sense, we present a version of neural precomputed radiance transfer that captures relighting of heterogeneous translucent objects. We use a multi-layer perceptron (MLP) with skip connections to represent the appearance of an object as a function of spatial position, direction of observation, and direction of incidence. The latter is considered a directional light incident across the entire non-self-shadowed part of the object. We demonstrate the ability of our method to compactly store highly complex materials while having high accuracy when comparing to reference images of the represented object in unseen lighting environments. As compared with path tracing of a heterogeneous light scattering volume behind a refractive interface, our method more easily enables importance sampling of the directions of incidence and can be integrated into existing rendering frameworks while achieving interactive frame rates.</p>\u0000 </div>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"43 7","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.15234","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142665050","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

Unerosion: Simulating Terrain Evolution Back in Time Unerosion：回到过去模拟地形演变

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-10-17 DOI: 10.1111/cgf.15182

Zhanyu Yang, Guillaume Cordonnier, Marie-Paule Cani, Christian Perrenoud, Bedrich Benes

{"title":"Unerosion: Simulating Terrain Evolution Back in Time","authors":"Zhanyu Yang, Guillaume Cordonnier, Marie-Paule Cani, Christian Perrenoud, Bedrich Benes","doi":"10.1111/cgf.15182","DOIUrl":"https://doi.org/10.1111/cgf.15182","url":null,"abstract":"<div>\u0000 \u0000 <p>While the past of terrain cannot be known precisely because an effect can result from many different causes, exploring these possible pasts opens the way to numerous applications ranging from movies and games to paleogeography. We introduce unerosion, an attempt to recover plausible past topographies from an input terrain represented as a height field. Our solution relies on novel algorithms for the backward simulation of different processes: fluvial erosion, sedimentation, and thermal erosion. This is achieved by re-formulating the equations of erosion and sedimentation so that they can be simulated back in time. These algorithms can be combined to account for a succession of climate changes backward in time, while the possible ambiguities provide editing options to the user. Results show that our solution can approximately reverse different types of erosion while enabling users to explore a variety of alternative pasts. Using a chronology of climatic periods to inform us about the main erosion phenomena, we also went back in time using real measured terrain data. We checked the consistency with geological findings, namely the height of river beds hundreds of thousands of years ago.</p>\u0000 </div>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"43 8","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.15182","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707654","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

ADAPT: AI-Driven Artefact Purging Technique for IMU Based Motion Capture ADAPT：基于 IMU 运动捕捉的人工智能驱动伪影清除技术

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-10-17 DOI: 10.1111/cgf.15172

P. Schreiner, R. Netterstrøm, H. Yin, S. Darkner, K. Erleben

{"title":"ADAPT: AI-Driven Artefact Purging Technique for IMU Based Motion Capture","authors":"P. Schreiner, R. Netterstrøm, H. Yin, S. Darkner, K. Erleben","doi":"10.1111/cgf.15172","DOIUrl":"https://doi.org/10.1111/cgf.15172","url":null,"abstract":"<div>\u0000 \u0000 <p>While IMU based motion capture offers a cost-effective alternative to premium camera-based systems, it often falls short in matching the latter's realism. Common distortions, such as self-penetrating body parts, foot skating, and floating, limit the usability of these systems, particularly for high-end users. To address this, we employed reinforcement learning to train an AI agent that mimics erroneous sample motion. Since our agent operates within a simulated environment, it inherently avoids generating these distortions since it must adhere to the laws of physics. Impressively, the agent manages to mimic the sample motions while preserving their distinctive characteristics. We assessed our method's efficacy across various types of input data, showcasing an ideal blend of artefact-laden IMU-based data with high-grade optical motion capture data. Furthermore, we compared the configuration of observation and action spaces with other implementations, pinpointing the most suitable configuration for our purposes. All our models underwent rigorous evaluation using a spectrum of quantitative metrics complemented by a qualitative review. These evaluations were performed using a benchmark dataset of IMU-based motion data from actors not included in the training data.</p>\u0000 </div>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"43 8","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.15172","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707689","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

Llanimation: Llama Driven Gesture Animation 动画拉玛驱动手势动画

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-10-17 DOI: 10.1111/cgf.15167

J. Windle, I. Matthews, S. Taylor

{"title":"Llanimation: Llama Driven Gesture Animation","authors":"J. Windle, I. Matthews, S. Taylor","doi":"10.1111/cgf.15167","DOIUrl":"https://doi.org/10.1111/cgf.15167","url":null,"abstract":"<div>\u0000 \u0000 <p>Co-speech gesturing is an important modality in conversation, providing context and social cues. In character animation, appropriate and synchronised gestures add realism, and can make interactive agents more engaging. Historically, methods for automatically generating gestures were predominantly audio-driven, exploiting the prosodic and speech-related content that is encoded in the audio signal. In this paper we instead experiment with using Large-Language Model (LLM) features for gesture generation that are extracted from text using <i>L<span>lama</span></i>2. We compare against audio features, and explore combining the two modalities in both objective tests and a user study. Surprisingly, our results show that <i>L<span>lama</span></i>2 features on their own perform significantly better than audio features and that including both modalities yields no significant difference to using <i>L<span>lama</span></i>2 features in isolation. We demonstrate that the <i>L<span>lama</span></i>2 based model can generate both beat and semantic gestures without any audio input, suggesting LLMs can provide rich encodings that are well suited for gesture generation.</p>\u0000 </div>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"43 8","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.15167","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707653","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

Generalized eXtended Finite Element Method for Deformable Cutting via Boolean Operations 通过布尔运算实现可变形切割的通用扩展有限元法

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-10-17 DOI: 10.1111/cgf.15184

Q. M. Ton-That, P. G. Kry, S. Andrews

{"title":"Generalized eXtended Finite Element Method for Deformable Cutting via Boolean Operations","authors":"Q. M. Ton-That, P. G. Kry, S. Andrews","doi":"10.1111/cgf.15184","DOIUrl":"https://doi.org/10.1111/cgf.15184","url":null,"abstract":"<div>\u0000 <p>Traditional mesh-based methods for cutting deformable bodies rely on modifying the simulation mesh by deleting, duplicating, deforming or subdividing its elements. Unfortunately, such topological changes eventually lead to instability, reduced accuracy, or computational efficiency challenges. Hence, state of the art algorithms favor the extended finite element method (XFEM), which decouples the cut geometry from the simulation mesh, allowing for stable and accurate cuts at an additional computational cost that is local to the cut region. However, in the 3-dimensional setting, current XFEM frameworks are limited by the cutting configurations that they support. In particular, intersecting cuts are either prohibited or require sophisticated special treatment. Our work presents a general XFEM formulation that is applicable to the 1-, 2-, and 3-dimensional setting without sacrificing the desirable properties of the method. In particular, we propose a generalized enrichment which supports multiple intersecting cuts of various degrees of non-linearity by leveraging recent advances in robust mesh-Boolean technology. This novel strategy additionally enables analytic discontinuous integration schemes required to compute mass, force and elastic energy. We highlight the simplicity, expressivity and accuracy of our XFEM implementation across various scenarios in which intersecting cutting patterns are featured.</p>\u0000 </div>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"43 8","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.15184","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707656","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

A Multi-layer Solver for XPBD XPBD 的多层求解器

IF 2.7 4区计算机科学

Computer Graphics Forum Pub Date : 2024-10-17 DOI: 10.1111/cgf.15186

A. Mercier-Aubin, P. G. Kry

引用次数: 0