中文
相关论文

相关论文: 3D Gaussian Inpainting with Depth-Guided Cross-Vie…

200 篇论文

Rendering and reconstruction are long-standing topics in computer vision and graphics. Achieving both high rendering quality and accurate geometry is a challenge. Recent advancements in 3D Gaussian Splatting (3DGS) have enabled…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Meng Wei , Qianyi Wu , Jianmin Zheng , Hamid Rezatofighi , Jianfei Cai

NeRF-based 3D-aware Generative Adversarial Networks (GANs) like EG3D or GIRAFFE have shown very high rendering quality under large representational variety. However, rendering with Neural Radiance Fields poses challenges for 3D…

计算机视觉与模式识别 · 计算机科学 2024-12-02 Florian Barthel , Arian Beckmann , Wieland Morgenstern , Anna Hilsmann , Peter Eisert

Accurate 3D reconstruction of dynamic surgical scenes from endoscopic video is essential for robotic-assisted surgery. While recent 3D Gaussian Splatting methods have shown promise in achieving high-quality reconstructions with fast…

计算机视觉与模式识别 · 计算机科学 2024-10-15 Jialei Chen , Xin Zhang , Mobarakol Islam , Francisco Vasconcelos , Danail Stoyanov , Daniel S. Elson , Baoru Huang

3D Gaussian Splatting (3D-GS) has emerged as a significant advancement in the field of Computer Graphics, offering explicit scene representation and novel view synthesis without the reliance on neural networks, such as Neural Radiance…

计算机视觉与模式识别 · 计算机科学 2024-07-11 Ben Fei , Jingyi Xu , Rui Zhang , Qingyuan Zhou , Weidong Yang , Ying He

Novel-view synthesis aims to generate novel views of a scene from multiple input images or videos, and recent advancements like 3D Gaussian splatting (3DGS) have achieved notable success in producing photorealistic renderings with efficient…

计算机视觉与模式识别 · 计算机科学 2024-10-22 Xi Liu , Chaoyi Zhou , Siyu Huang

Reconstructing 3D assets from images, known as inverse rendering (IR), remains a challenging task due to its ill-posed nature. 3D Gaussian Splatting (3DGS) has demonstrated impressive capabilities for novel view synthesis (NVS) tasks.…

计算机视觉与模式识别 · 计算机科学 2025-04-10 Hanxiao Sun , YuPeng Gao , Jin Xie , Jian Yang , Beibei Wang

3D Gaussian Splatting has recently emerged as an efficient solution for high-quality and real-time novel view synthesis. However, its capability for accurate surface reconstruction remains underexplored. Due to the discrete and unstructured…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Qing Li , Huifang Feng , Xun Gong , Yu-Shen Liu

The field of 3D reconstruction from images has rapidly evolved in the past few years, first with the introduction of Neural Radiance Field (NeRF) and more recently with 3D Gaussian Splatting (3DGS). The latter provides a significant edge…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Avinash Paliwal , Wei Ye , Jinhui Xiong , Dmytro Kotovenko , Rakesh Ranjan , Vikas Chandra , Nima Khademi Kalantari

In this paper, we propose a 3D geometry-aware deformable Gaussian Splatting method for dynamic view synthesis. Existing neural radiance fields (NeRF) based solutions learn the deformation in an implicit manner, which cannot incorporate 3D…

计算机视觉与模式识别 · 计算机科学 2024-04-16 Zhicheng Lu , Xiang Guo , Le Hui , Tianrui Chen , Min Yang , Xiao Tang , Feng Zhu , Yuchao Dai

Recently, 3D Gaussian Splatting (3DGS) has enabled photorealistic view synthesis at high inference speeds. However, its splatting-based rendering model makes several approximations to the rendering equation, reducing physical accuracy. We…

计算机视觉与模式识别 · 计算机科学 2025-05-22 Chinmay Talegaonkar , Yash Belhe , Ravi Ramamoorthi , Nicholas Antipa

We propose two novel ideas (adoption of deferred rendering and mesh-based representation) to improve the quality of 3D Gaussian splatting (3DGS) based inverse rendering. We first report a problem incurred by hidden Gaussians, where…

图形学 · 计算机科学 2024-09-17 Euntae Choi , Sungjoo Yoo

3D scene representations have gained immense popularity in recent years. Methods that use Neural Radiance fields are versatile for traditional tasks such as novel view synthesis. In recent times, some work has emerged that aims to extend…

计算机视觉与模式识别 · 计算机科学 2024-04-09 Shijie Zhou , Haoran Chang , Sicheng Jiang , Zhiwen Fan , Zehao Zhu , Dejia Xu , Pradyumna Chari , Suya You , Zhangyang Wang , Achuta Kadambi

Gaussian Splatting (GS) offers a promising alternative to Neural Radiance Fields (NeRF) for real-time 3D scene rendering. Using a set of 3D Gaussians to represent complex geometry and appearance, GS achieves faster rendering times and…

多媒体 · 计算机科学 2025-06-18 Pedro Martin , António Rodrigues , João Ascenso , Maria Paula Queluz

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

In the context of novel view synthesis, 3D Gaussian Splatting (3DGS) has recently emerged as an efficient and competitive counterpart to Neural Radiance Field (NeRF), enabling high-fidelity photorealistic rendering in real time. Beyond…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Shuting He , Peilin Ji , Yitong Yang , Changshuo Wang , Jiayi Ji , Yinglin Wang , Henghui Ding

We address the problem of 3D inconsistency of image inpainting based on diffusion models. We propose a generative model using image pairs that belong to the same scene. To achieve the 3D-consistent and semantically coherent inpainting, we…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Leonid Antsfeld , Boris Chidlovskii

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

We introduce NeRF-GS, a novel framework that jointly optimizes Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). This framework leverages the inherent continuous spatial representation of NeRF to mitigate several limitations…

计算机视觉与模式识别 · 计算机科学 2025-08-01 Shuangkang Fang , I-Chao Shen , Takeo Igarashi , Yufeng Wang , ZeSheng Wang , Yi Yang , Wenrui Ding , Shuchang Zhou

Novel-view synthesis based on visible light has been extensively studied. In comparison to visible light imaging, thermal infrared imaging offers the advantage of all-weather imaging and strong penetration, providing increased possibilities…

计算机视觉与模式识别 · 计算机科学 2024-09-13 Qian Chen , Shihao Shu , Xiangzhi Bai

3D Gaussian Splatting is crucial for real-time novel view synthesis due to its efficiency and ability to render photorealistic images. However, building a 3D Gaussian is guided solely by photometric loss, which can result in inconsistencies…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Quan Tran , Tuan Dang