⚠️ 以下所有内容总结都来自于 大语言模型的能力,如有错误,仅供参考,谨慎使用
🔴 请注意:千万不要用于严肃的学术场景,只能用于论文阅读前的初筛!
💗 如果您觉得我们的项目对您有帮助 ChatPaperFree ,还请您给我们一些鼓励!⭐️ HuggingFace免费体验
2025-11-21 更新
Gaussian Blending: Rethinking Alpha Blending in 3D Gaussian Splatting
Authors:Junseo Koo, Jinseo Jeong, Gunhee Kim
The recent introduction of 3D Gaussian Splatting (3DGS) has significantly advanced novel view synthesis. Several studies have further improved the rendering quality of 3DGS, yet they still exhibit noticeable visual discrepancies when synthesizing views at sampling rates unseen during training. Specifically, they suffer from (i) erosion-induced blurring artifacts when zooming in and (ii) dilation-induced staircase artifacts when zooming out. We speculate that these artifacts arise from the fundamental limitation of the alpha blending adopted in 3DGS methods. Instead of the conventional alpha blending that computes alpha and transmittance as scalar quantities over a pixel, we propose to replace it with our novel Gaussian Blending that treats alpha and transmittance as spatially varying distributions. Thus, transmittances can be updated considering the spatial distribution of alpha values across the pixel area, allowing nearby background splats to contribute to the final rendering. Our Gaussian Blending maintains real-time rendering speed and requires no additional memory cost, while being easily integrated as a drop-in replacement into existing 3DGS-based or other NVS frameworks. Extensive experiments demonstrate that Gaussian Blending effectively captures fine details at various sampling rates unseen during training, consistently outperforming existing novel view synthesis models across both unseen and seen sampling rates.
近期引入的3D高斯延展(3DGS)技术极大地推动了新型视图合成的进步。尽管已有若干研究进一步提高了3DGS的渲染质量,但它们仍然展现出合成未见过采样率的视图时明显的视觉差异。具体来说,它们在(i)放大时会出现因侵蚀导致的模糊伪影,以及在(ii)缩小时出现因膨胀导致的阶梯状伪影。我们推测这些伪影源于3DGS方法中使用的alpha混合的基本局限性。我们提出用新型的高斯混合方法取代传统的alpha混合,后者会在像素上计算标量形式的alpha和透射率。我们的高斯混合将alpha和透射率视为空间变化的分布。因此,在考虑像素区域内alpha值的空间分布后,可以更新透射率,允许附近的背景展点有助于最终渲染。我们的高斯混合保持实时渲染速度,无需额外的内存成本,且易于集成到现有的基于3DGS或其他新型视图合成框架中作为插件进行替换。大量实验表明,高斯混合在训练期间未见的各种采样率下有效地捕捉到了细节,并且在未见和已见采样率的情况下均始终优于现有的新型视图合成模型。
论文及项目相关链接
PDF AAAI 2026
Summary
该摘要提出一种全新的观点合成方法,利用改进的混合策略即高斯混合取代原有的α混合算法来克服传统的限制问题,有效地减少了放大时的模糊伪影和缩小时的阶梯效应,显著提高视图的合成质量。新的高斯混合算法实现了对原有模型的高实时渲染性能、无额外内存需求等优点。总的来说,该技术能有效解决在训练未见采样率下的视角合成问题,显著优于现有技术。
Key Takeaways
以下是七个关键要点:
- 引入的3D高斯贴图技术(3DGS)已对新颖视角合成产生了重要影响。
点此查看论文截图
Gaussian See, Gaussian Do: Semantic 3D Motion Transfer from Multiview Video
Authors:Yarin Bekor, Gal Michael Harari, Or Perel, Or Litany
We present Gaussian See, Gaussian Do, a novel approach for semantic 3D motion transfer from multiview video. Our method enables rig-free, cross-category motion transfer between objects with semantically meaningful correspondence. Building on implicit motion transfer techniques, we extract motion embeddings from source videos via condition inversion, apply them to rendered frames of static target shapes, and use the resulting videos to supervise dynamic 3D Gaussian Splatting reconstruction. Our approach introduces an anchor-based view-aware motion embedding mechanism, ensuring cross-view consistency and accelerating convergence, along with a robust 4D reconstruction pipeline that consolidates noisy supervision videos. We establish the first benchmark for semantic 3D motion transfer and demonstrate superior motion fidelity and structural consistency compared to adapted baselines. Code and data for this paper available at https://gsgd-motiontransfer.github.io/
我们提出了一种新的方法——Gaussian See和Gaussian Do,用于从多视角视频进行语义3D动作迁移。我们的方法能够实现无骨架、跨类别的对象间语义对应的动作迁移。我们基于隐式动作迁移技术,通过条件反转从源视频中抽取动作嵌入信息,将其应用于静态目标形状的渲染帧,并使用所得视频来监督动态3D高斯贴图重建。我们的方法引入了一种基于锚点的视角感知动作嵌入机制,确保跨视角的一致性并加速收敛,同时建立一个稳健的4D重建流程来整合噪声监督视频。我们建立了第一个语义3D动作迁移的基准测试,并展示了相比于适应性基准的高超动作保真度和结构一致性。这篇论文的代码和数据可在https://gsgd-motiontransfer.github.io/找到。
论文及项目相关链接
PDF SIGGRAPH Asia 2025
Summary
该文提出一种基于高斯分裂技术的全新三维语义动作转移方法,该方法可以从多角度视频中提取动态运动的嵌入信息,并将其应用于静态目标形状的渲染帧上。通过引入锚点视角感知的运动嵌入机制,确保了跨视角的一致性和加速收敛。同时,该文还建立了一个针对语义三维动作转移的首个基准测试集,并展示了相较于其他基线方法更高的动作保真度和结构一致性。
Key Takeaways
- 该文提出了一种新颖的语义三维动作转移方法,称为高斯看、高斯做(Gaussian See, Gaussian Do)。
- 方法基于隐式动作转移技术,通过条件反转从源视频中抽取运动嵌入信息。
- 该方法应用于静态目标形状的渲染帧上,并使用结果视频来监督动态三维高斯分裂重建。
- 引入锚点视角感知的运动嵌入机制确保了跨视角的一致性和加速收敛。
- 建立了一个针对语义三维动作转移的首个基准测试集。
- 与适应的基线相比,该方法展示更高的动作保真度和结构一致性。
点此查看论文截图
Gaussian Splatting-based Low-Rank Tensor Representation for Multi-Dimensional Image Recovery
Authors:Yiming Zeng, Xi-Le Zhao, Wei-Hao Wu, Teng-Yu Ji, Chao Wang
Tensor singular value decomposition (t-SVD) is a promising tool for multi-dimensional image representation, which decomposes a multi-dimensional image into a latent tensor and an accompanying transform matrix. However, two critical limitations of t-SVD methods persist: (1) the approximation of the latent tensor (e.g., tensor factorizations) is coarse and fails to accurately capture spatial local high-frequency information; (2) The transform matrix is composed of fixed basis atoms (e.g., complex exponential atoms in DFT and cosine atoms in DCT) and cannot precisely capture local high-frequency information along the mode-3 fibers. To address these two limitations, we propose a Gaussian Splatting-based Low-rank tensor Representation (GSLR) framework, which compactly and continuously represents multi-dimensional images. Specifically, we leverage tailored 2D Gaussian splatting and 1D Gaussian splatting to generate the latent tensor and transform matrix, respectively. The 2D and 1D Gaussian splatting are indispensable and complementary under this representation framework, which enjoys a powerful representation capability, especially for local high-frequency information. To evaluate the representation ability of the proposed GSLR, we develop an unsupervised GSLR-based multi-dimensional image recovery model. Extensive experiments on multi-dimensional image recovery demonstrate that GSLR consistently outperforms state-of-the-art methods, particularly in capturing local high-frequency information.
张量奇异值分解(t-SVD)是多维图像表示的一种有前途的工具,它将多维图像分解为一个潜在张量和一个伴随的转换矩阵。然而,t-SVD方法存在两个关键局限性:(1)潜在张量的近似(例如,张量分解)是粗糙的,无法准确捕获空间局部高频信息;(2)转换矩阵由固定基础原子(例如,DFT中的复数指数原子和DCT中的余弦原子)组成,无法精确捕获模式3纤维上的局部高频信息。为了解决这两个局限性,我们提出了基于高斯涂敷的低秩张量表示(GSLR)框架,该框架能够紧凑且连续地表示多维图像。具体来说,我们利用定制的2D高斯涂敷和1D高斯涂敷来生成潜在张量和转换矩阵。在这种表示框架下,2D和1D高斯涂敷是必不可少的且互补的,具有强大的表示能力,尤其对于局部高频信息。为了评估所提出的GSLR的表示能力,我们开发了一个基于无监督GSLR的多维图像恢复模型。多维图像恢复的广泛实验表明,GSLR始终优于最先进的方法,特别是在捕获局部高频信息方面。
论文及项目相关链接
Summary
基于张量奇异值分解(t-SVD)的多维图像表示方法存在两个关键局限:一是潜在张量的近似处理不够精细,无法准确捕捉空间局部高频信息;二是变换矩阵由固定基原子组成,无法精确捕捉模式三纤维的局部高频信息。为解决这些问题,我们提出了基于高斯展开的低秩张量表示(GSLR)框架,能够紧凑且连续地表示多维图像。该框架利用定制的二维和一维高斯展开生成潜在张量和变换矩阵,二者在此框架中不可或缺且相互补充,尤其擅长表示局部高频信息。实验证明,GSLR在多维图像恢复上的表现优于现有方法,特别是在捕捉局部高频信息方面。
Key Takeaways
- t-SVD用于多维图像表示存在两个主要局限:潜在张量近似处理不精细,变换矩阵无法精确捕捉局部高频信息。
- GSLR框架解决了这些问题,通过定制的二维和一维高斯展开生成潜在张量和变换矩阵,实现多维图像的更紧凑和连续表示。
- GSLR特别擅长表示局部高频信息,在多维图像恢复方面的表现优于现有方法。
- 2D和1D高斯展开在GSLR框架中不可或缺且相互补充。
点此查看论文截图
SymGS : Leveraging Local Symmetries for 3D Gaussian Splatting Compression
Authors:Keshav Gupta, Akshat Sanghvi, Shreyas Reddy Palley, Astitva Srivastava, Charu Sharma, Avinash Sharma
3D Gaussian Splatting has emerged as a transformative technique in novel view synthesis, primarily due to its high rendering speed and photorealistic fidelity. However, its memory footprint scales rapidly with scene complexity, often reaching several gigabytes. Existing methods address this issue by introducing compression strategies that exploit primitive-level redundancy through similarity detection and quantization. We aim to surpass the compression limits of such methods by incorporating symmetry-aware techniques, specifically targeting mirror symmetries to eliminate redundant primitives. We propose a novel compression framework, SymGS, introducing learnable mirrors into the scene, thereby eliminating local and global reflective redundancies for compression. Our framework functions as a plug-and-play enhancement to state-of-the-art compression methods, (e.g. HAC) to achieve further compression. Compared to HAC, we achieve $1.66 \times$ compression across benchmark datasets (upto $3\times$ on large-scale scenes). On an average, SymGS enables $\bf{108\times}$ compression of a 3DGS scene, while preserving rendering quality. The project page and supplementary can be found at symgs.github.io
3D高斯模糊技术已在新视角合成中成为一种变革性的技术,这主要得益于其高渲染速度和逼真的保真度。然而,其内存占用随着场景的复杂性而迅速增长,经常达到数GB。现有方法通过引入利用基于相似性检测和量化的基本冗余元素压缩策略来解决此问题。我们的目标是利用对称性技术突破现有方法的压缩限制,专门采用镜像对称来消除冗余元素。我们提出了一种新型压缩框架SymGS,通过引入场景中的可学习镜像,消除局部和全局反射冗余以实现压缩。我们的框架作为一个增强插件,可以嵌入到最新压缩方法(如HAC)中,以实现进一步的压缩。与HAC相比,我们在基准数据集上实现了$1.66 \times$的压缩(大规模场景上最多为$3\times$)。平均而言,SymGS实现了高达$\bf{108\times}$的3DGS场景压缩,同时保持渲染质量不变。项目页面和补充材料可在symgs.github.io找到。
论文及项目相关链接
PDF Project Page: https://symgs.github.io/
Summary
3D Gaussian Splatting在新型视图合成中展现出了变革性的技术,以其高渲染速度和逼真的画质著称。但其内存占用随着场景复杂度快速增加,达到数GB。现有方法通过引入压缩策略解决这一问题,利用基本单元的冗余性进行相似性检测和量化。我们的目标是超越此类方法的压缩极限,通过融入对称性感知技术,特别是针对镜像对称性消除冗余基本单元。我们提出了一种新型压缩框架SymGS,引入可学习镜像至场景,从而消除局部和全局反射冗余以实现压缩。该框架可作为最先进的压缩方法的插件进行增强(如HAC),以实现更高的压缩效果。相比HAC,我们在基准数据集上实现了1.66倍的压缩(大规模场景上最高可达3倍)。平均而言,SymGS实现了3DGS场景的108倍压缩,同时保持渲染质量。
Key Takeaways
- 3D Gaussian Splatting在视图合成中表现出卓越性能。
- 现有方法主要利用基本单元的冗余性进行压缩。
- SymGS通过融入对称性感知技术尤其是镜像对称性优化压缩性能。
- SymGS引入可学习镜像至场景以消除反射冗余。
- SymGS可作为现有压缩方法的插件增强使用。
- 与HAC相比,SymGS在基准数据集上实现了更高的压缩效果。
点此查看论文截图
Arbitrary-Scale 3D Gaussian Super-Resolution
Authors:Huimin Zeng, Yue Bai, Yun Fu
Existing 3D Gaussian Splatting (3DGS) super-resolution methods typically perform high-resolution (HR) rendering of fixed scale factors, making them impractical for resource-limited scenarios. Directly rendering arbitrary-scale HR views with vanilla 3DGS introduces aliasing artifacts due to the lack of scale-aware rendering ability, while adding a post-processing upsampler for 3DGS complicates the framework and reduces rendering efficiency. To tackle these issues, we build an integrated framework that incorporates scale-aware rendering, generative prior-guided optimization, and progressive super-resolving to enable 3D Gaussian super-resolution of arbitrary scale factors with a single 3D model. Notably, our approach supports both integer and non-integer scale rendering to provide more flexibility. Extensive experiments demonstrate the effectiveness of our model in rendering high-quality arbitrary-scale HR views (6.59 dB PSNR gain over 3DGS) with a single model. It preserves structural consistency with LR views and across different scales, while maintaining real-time rendering speed (85 FPS at 1080p).
现有的3D高斯拼贴(3DGS)超分辨率方法通常对固定比例因子进行高分辨率(HR)渲染,这在资源受限的场景中不太实用。直接使用普通的3DGS进行任意比例的HR视图渲染,由于缺乏比例感知渲染能力,会出现混叠伪影。而为3DGS添加后处理上采样器会复杂化框架并降低渲染效率。为了解决这些问题,我们构建了一个集成框架,该框架结合了比例感知渲染、生成先验引导优化和渐进超分辨率技术,以使用单个3D模型实现任意比例的3D高斯超分辨率。值得注意的是,我们的方法支持整数和非整数比例渲染,以提供更灵活的选项。大量实验表明,我们的模型在渲染高质量任意比例HR视图方面非常有效(比3DGS高出6.59 dB PSNR)。我们的模型在保持与LR视图的结构一致性的同时,能在不同尺度上保持实时渲染速度(1080p下85 FPS)。
论文及项目相关链接
PDF Accepted to AAAI 2026
Summary
该文针对现有3D高斯混合(3DGS)超分辨率方法存在的问题,提出了一种集成框架,融合了尺度感知渲染、生成先验引导优化和渐进超分辨率技术,实现了单3D模型的任意尺度因子3D高斯超分辨率。该方法支持整数和非整数尺度渲染,提高了渲染质量和灵活性。实验表明,该方法在单模型下实现了高质量任意尺度高分辨率视图渲染,较传统3DGS有6.59 dB PSNR增益,同时保持了实时渲染速度。
Key Takeaways
- 现有3DGS方法存在固定尺度因子渲染限制,不适用于资源受限场景。
- 单一3DGS直接渲染任意尺度高分辨率视图会产生混叠伪影。
- 提出的集成框架融合了尺度感知渲染、生成先验引导优化和渐进超分辨率技术。
- 方法支持整数和非整数尺度渲染,提高灵活性。
- 实验证明,该方法在单模型下实现了高质量任意尺度高分辨率视图渲染。
- 较传统3DGS有6.59 dB PSNR增益。
点此查看论文截图
6D Rigid Body Localization and Velocity Estimation via Gaussian Belief Propagation
Authors:Niclas Führling, Volodymyr Vizitiv, Kuranage Roche Rayan Ranasinghe, Hyeon Seok Rou, Giuseppe Thadeu Freitas de Abreu, David González G., Osvaldo Gonsa
We propose a novel message-passing solution to the sixth-dimensional (6D) moving rigid body localization (RBL) problem, in which the three-dimensional (3D) translation vector and rotation angles, as well as their corresponding translational and angular velocities, are all estimated by only utilizing the relative range and Doppler measurements between the “anchor” sensors located at an 3D (rigid body) observer and the “target” sensors of another rigid body. The proposed method is based on a bilinear Gaussian belief propagation (GaBP) framework, employed to estimate the absolute sensor positions and velocities using a range- and Doppler-based received signal model, which is then utilized in the reconstruction of the RBL transformation model, linearized under a small-angle approximation. The method further incorporates a second bivariate GaBP designed to directly estimate the 3D rotation angles and translation vectors, including an interference cancellation (IC) refinement stage to improve the angle estimation performance, followed by the estimation of the angular and the translational velocities. The effectiveness of the proposed method is verified via simulations, which confirms its improved performance compared to equivalent state-of-the-art (SotA) techniques.
我们针对六维(6D)移动刚体定位(RBL)问题提出了一种新型的消息传递解决方案。在此问题中,仅利用位于三维(刚体)观察者与另一个刚体的“目标”传感器之间的相对距离和Doppler测量值,来估计三维平移向量和旋转角度,以及它们对应的平移和角速度。所提方法基于双线性高斯信念传播(GaBP)框架,用于根据基于距离和Doppler的接收信号模型估计绝对传感器位置和速度,然后将其用于重建RBL转换模型,在小角度近似下实现线性化。该方法还结合了第二个双变量GaBP,用于直接估计三维旋转角度和平移向量,包括一个干扰消除(IC)优化阶段,以提高角度估计性能,然后进行角和平移速度的估计。通过模拟验证了所提方法的有效性,模拟结果证明了其相较于现有先进技术(SotA)的优越性能。
论文及项目相关链接
PDF arXiv admin note: text overlap with arXiv:2407.09232
Summary
本文提出一种新型消息传递算法解决六维空间中的动态刚体定位问题,利用相对测距和多普雷达测量估计三维平移向量和旋转角度以及对应的速度和角速度。该方法基于双线性高斯信念传播算法框架,利用测距和多普雷达接收信号模型估计绝对传感器位置和速度,并重建在小角度近似下线性化的刚体定位转换模型。该方法还包含第二个双变量高斯信念传播算法,用于直接估计三维旋转角度和平移向量,并采用干扰消除细化阶段以提高角度估计性能,最终完成速度和角速度的估计。模拟验证显示此方法较当前先进技术的性能有所提升。
Key Takeaways
- 提出一种解决六维空间中刚体定位问题的新型消息传递算法。
- 利用相对测距和多普雷达测量进行三维平移向量和旋转角度的估计。
- 基于双线性高斯信念传播算法框架,利用测距和多普雷达信号模型估计传感器位置和速度。
- 在小角度近似下重建刚体定位转换模型。
- 采用第二个双变量高斯信念传播算法直接估计三维旋转角度和平移向量。
- 细化阶段采用干扰消除技术提高角度估计性能。