中文
相关论文

相关论文: SpotlessSplats: Ignoring Distractors in 3D Gaussia…

200 篇论文

3D Gaussian Splatting (3DGS) has recently gained popularity for efficient scene rendering by representing scenes as explicit sets of anisotropic 3D Gaussians. However, most existing work focuses primarily on modeling external surfaces. In…

图像与视频处理 · 电气工程与系统科学 2026-01-12 Shuxin Liang , Yihan Xiao , Wenlu Tang

The recent success of 3D Gaussian Splatting (3DGS) has reshaped novel view synthesis by enabling fast optimization and real-time rendering of high-quality radiance fields. However, it relies on simplified, order-dependent alpha blending and…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Jan U. Müller , Robin Tim Landsgesell , Leif Van Holland , Patrick Stotko , Reinhard Klein

Gaussian splatting typically requires dense observations of the scene and can fail to reconstruct occluded and unobserved areas. We propose a latent diffusion model to reconstruct a complete 3D scene with Gaussian splats, including the…

计算机视觉与模式识别 · 计算机科学 2025-09-01 Ziwei Liao , Mohamed Sayed , Steven L. Waslander , Sara Vicente , Daniyar Turmukhambetov , Michael Firman

3D Gaussian Splatting (3DGS) demonstrates unparalleled superior performance in 3D scene reconstruction. However, 3DGS heavily relies on the sharp images. Fulfilling this requirement can be challenging in real-world scenarios especially when…

计算机视觉与模式识别 · 计算机科学 2024-12-25 Yijia Guo , Liwen Hu , Yuanxi Bai , Jiawei Yao , Lei Ma , Tiejun Huang

Dynamic scene reconstruction has garnered significant attention in recent years due to its capabilities in high-quality and real-time rendering. Among various methodologies, constructing a 4D spatial-temporal representation, such as 4D-GS,…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Weiwei Cai , Weicai Ye , Peng Ye , Tong He , Tao Chen

With the rapid advancement of 3D visualization, 3D Gaussian Splatting (3DGS) has emerged as a leading technique for real-time, high-fidelity rendering. While prior research has emphasized algorithmic performance and visual fidelity, the…

计算机视觉与模式识别 · 计算机科学 2025-11-12 Zhaolin Wan , Yining Diao , Jingqi Xu , Hao Wang , Zhiyang Li , Xiaopeng Fan , Wangmeng Zuo , Debin Zhao

Reconstructing clean, distractor-free 3D scenes from real-world captures remains a significant challenge, particularly in highly dynamic and cluttered settings such as egocentric videos. To tackle this problem, we introduce DeGauss, a…

计算机视觉与模式识别 · 计算机科学 2025-07-25 Rui Wang , Quentin Lohmeyer , Mirko Meboldt , Siyu Tang

Implicit neural representation has paved the way for new approaches to dynamic scene reconstruction and rendering. Nonetheless, cutting-edge dynamic neural rendering methods rely heavily on these implicit representations, which frequently…

计算机视觉与模式识别 · 计算机科学 2023-11-22 Ziyi Yang , Xinyu Gao , Wen Zhou , Shaohui Jiao , Yuqing Zhang , Xiaogang Jin

3D Gaussian Splatting (3DGS) has gained significant attention for its high-quality rendering capabilities, ultra-fast training, and inference speeds. However, when we apply 3DGS to surface reconstruction tasks, especially in environments…

计算机视觉与模式识别 · 计算机科学 2025-03-14 Chenfeng Hou , Qi Xun Yeo , Mengqi Guo , Yongxin Su , Yanyan Li , Gim Hee Lee

Gaussian Splatting (GS) has become one of the most important neural rendering algorithms. GS represents 3D scenes using Gaussian components with trainable color and opacity. This representation achieves high-quality renderings with fast…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Krzysztof Byrski , Grzegorz Wilczyński , Weronika Smolak-Dyżewska , Piotr Borycki , Dawid Baran , Sławomir Tadeja , Przemysław Spurek

Gaussian Splatting (GS) has proven to be highly effective in novel view synthesis, achieving high-quality and real-time rendering. However, its potential for reconstructing detailed 3D shapes has not been fully explored. Existing methods…

图形学 · 计算机科学 2024-06-25 Baowen Zhang , Chuan Fang , Rakesh Shrestha , Yixun Liang , Xiaoxiao Long , Ping Tan

Real-time reconstruction of deformable surgical scenes is vital for advancing robotic surgery, improving surgeon guidance, and enabling automation. Recent methods achieve dense reconstructions from da Vinci robotic surgery videos, with…

计算机视觉与模式识别 · 计算机科学 2026-02-23 Tianyi Song , Danail Stoyanov , Evangelos Mazomenos , Francisco Vasconcelos

3D Gaussian splatting (3DGS) is a popular radiance field method, with many application-specific extensions. Most variants rely on the same core algorithm: depth-sorting of Gaussian splats then rasterizing in primitive order. This ensures…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Shakiba Kheradmand , Delio Vicini , George Kopanas , Dmitry Lagun , Kwang Moo Yi , Mark Matthews , Andrea Tagliasacchi

3D Gaussian Splatting (3DGS) has emerged as a promising approach for 3D scene representation, offering a reduction in computational overhead compared to Neural Radiance Fields (NeRF). However, 3DGS is susceptible to high-frequency artifacts…

计算机视觉与模式识别 · 计算机科学 2024-09-06 Shen Chen , Jiale Zhou , Lei Li

3D Gaussian Splatting (3DGS) enables real-time novel view synthesis with high visual quality. However, existing methods struggle with semi-transparent specular surfaces that exhibit both complex reflections and clear transmission, often…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Ji Shi , Xianghua Ying , Bowei Xing , Ruohao Guo , Wenzhen Yue

3D Gaussian Splatting has achieved impressive performance in novel view synthesis with real-time rendering capabilities. However, reconstructing high-quality surfaces with fine details using 3D Gaussians remains a challenging task. In this…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Jiepeng Wang , Yuan Liu , Peng Wang , Cheng Lin , Junhui Hou , Xin Li , Taku Komura , Wenping Wang

Recent years have witnessed substantial advancements in the field of 3D reconstruction from 2D images, particularly following the introduction of the neural radiance field (NeRF) technique. However, reconstructing a 3D high dynamic range…

计算机视觉与模式识别 · 计算机科学 2024-11-05 Jiahao Wu , Lu Xiao , Rui Peng , Kaiqiang Xiong , Ronggang Wang

While 3D Gaussian Splatting (3DGS) achieves real-time photorealistic rendering, its performance degrades significantly when training images contain transient objects that violate multi-view consistency. Existing methods face a circular…

计算机视觉与模式识别 · 计算机科学 2026-04-24 Xu Wang , Zhiru Wang , Shiyun Xie , Chengwei Pan , Yisong Chen

The problem of 3D reconstruction from posed images is undergoing a fundamental transformation, driven by continuous advances in 3D Gaussian Splatting (3DGS). By modeling scenes explicitly as collections of 3D Gaussians, 3DGS enables…

计算机视觉与模式识别 · 计算机科学 2026-03-02 Vitor Pereira Matias , Daniel Perazzo , Vinicius Silva , Alberto Raposo , Luiz Velho , Afonso Paiva , Tiago Novello

3D Gaussian Splatting (3DGS) has emerged as a prominent technique with the potential to become a mainstream method for 3D representations. It can effectively transform multi-view images into explicit 3D Gaussian through efficient training,…

计算机视觉与模式识别 · 计算机科学 2024-12-18 Yanqi Bao , Tianyu Ding , Jing Huo , Yaoli Liu , Yuxin Li , Wenbin Li , Yang Gao , Jiebo Luo