中文
相关论文

相关论文: HoloGS: Instant Depth-based 3D Gaussian Splatting …

200 篇论文

Generalizable 3D Gaussian Splatting reconstruction showcases advanced Image-to-3D content creation but requires substantial computational resources and large datasets, posing challenges to training models from scratch. Current methods…

计算机视觉与模式识别 · 计算机科学 2026-01-05 Xiufeng Huang , Ka Chun Cheung , Runmin Cong , Simon See , Renjie Wan

Recent advancements in 3D Gaussian Splatting (3DGS) have substantially improved novel view synthesis, enabling high-quality reconstruction and real-time rendering. However, blurring artifacts, such as floating primitives and…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Haodong Chen , Runnan Chen , Qiang Qu , Zhaoqing Wang , Tongliang Liu , Xiaoming Chen , Yuk Ying Chung

3D Gaussian Splatting (3DGS) has demonstrated impressive performance in 3D scene reconstruction. Beyond novel view synthesis, it shows great potential for multi-view surface reconstruction. Existing methods employ optimization-based…

计算机视觉与模式识别 · 计算机科学 2026-04-10 Chensheng Dai , Shengjun Zhang , Min Chen , Yueqi Duan

We present the first application of 3D Gaussian Splatting in monocular SLAM, the most fundamental but the hardest setup for Visual SLAM. Our method, which runs live at 3fps, utilises Gaussians as the only 3D representation, unifying the…

计算机视觉与模式识别 · 计算机科学 2024-04-16 Hidenobu Matsuki , Riku Murai , Paul H. J. Kelly , Andrew J. Davison

3D Gaussian Splats (3DGS) have proven a versatile rendering primitive, both for inverse rendering as well as real-time exploration of scenes. In these applications, coherence across camera frames and multiple views is crucial, be it for…

Recently, 3D Gaussian splatting (3D-GS) has gained popularity in novel-view scene synthesis. It addresses the challenges of lengthy training times and slow rendering speeds associated with Neural Radiance Fields (NeRFs). Through rapid,…

计算机视觉与模式识别 · 计算机科学 2024-09-27 Sharath Girish , Kamal Gupta , Abhinav Shrivastava

Empowering 3D Gaussian Splatting with generalization ability is appealing. However, existing generalizable 3D Gaussian Splatting methods are largely confined to narrow-range interpolation between stereo images due to their heavy backbones,…

计算机视觉与模式识别 · 计算机科学 2024-10-30 Yunsong Wang , Tianxin Huang , Hanlin Chen , Gim Hee Lee

3D Gaussian Splatting (3DGS) has emerged as a powerful explicit representation enabling real-time, high-fidelity 3D reconstruction and novel view synthesis. However, its practical use is hindered by the massive memory and computational…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Seokhyun Youn , Soohyun Lee , Geonho Kim , Weeyoung Kwon , Sung-Ho Bae , Jihyong Oh

We perceive our surroundings with an active focus, paying more attention to regions of interest, such as the shelf labels in a grocery store. When it comes to scene reconstruction, this human perception trait calls for spatially varying…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Yijia Weng , Zhicheng Wang , Songyou Peng , Saining Xie , Howard Zhou , Leonidas J. Guibas

In underwater images, most useful features are occluded by water. The extent of the occlusion depends on imaging geometry and can vary even across a sequence of burst images. As a result, 3D reconstruction methods robust on in-air scenes,…

计算机视觉与模式识别 · 计算机科学 2025-11-04 Nir Mualem , Roy Amoyal , Oren Freifeld , Derya Akkaynak

3D Gaussian Splatting (3DGS) has emerged as a promising 3D reconstruction technique. The traditional 3DGS training pipeline follows three sequential steps: Gaussian densification, Gaussian projection, and color splatting. Despite its…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Junyi Wu , Jiaming Xu , Jinhao Li , Yongkang Zhou , Jiayi Pan , Xingyang Li , Guohao Dai

3D Gaussian Splatting (GS) enables highly photorealistic scene reconstruction from posed image sequences but struggles with viewpoint extrapolation due to its anisotropic nature, leading to overfitting and poor generalization, particularly…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Shuohan Tao , Boyao Zhou , Hanzhang Tu , Yuwang Wang , Yebin Liu

Recently, 3D Gaussian Splatting (3DGS) has excelled in novel view synthesis (NVS) with its real-time rendering capabilities and superior quality. However, it encounters challenges for high-resolution novel view synthesis (HRNVS) due to the…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Shiyun Xie , Zhiru Wang , Yinghao Zhu , Xu Wang , Chengwei Pan , Xiwang Dong

Digitizing 3D static scenes and 4D dynamic events from multi-view images has long been a challenge in computer vision and graphics. Recently, 3D Gaussian Splatting (3DGS) has emerged as a practical and scalable reconstruction method,…

计算机视觉与模式识别 · 计算机科学 2024-09-18 Marko Mihajlovic , Sergey Prokudin , Siyu Tang , Robert Maier , Federica Bogo , Tony Tung , Edmond Boyer

Gaussian Splatting has emerged as a leading method for novel view synthesis, offering superior training efficiency and real-time inference compared to NeRF approaches, while still delivering high-quality reconstructions. Beyond view…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Lorenzo Rutayisire , Nicola Capodieci , Fabio Pellacini

Reconstructing transparent surfaces is essential for tasks such as robotic manipulation in labs, yet it poses a significant challenge for 3D reconstruction techniques like 3D Gaussian Splatting (3DGS). These methods often encounter a…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Mingwei Li , Pu Pang , Hehe Fan , Hua Huang , Yi Yang

Image data captured outdoors often exhibit unbounded scenes and unconstrained, varying lighting conditions, making it challenging to decompose them into geometry, reflectance, and illumination. Recent works have focused on achieving this…

计算机视觉与模式识别 · 计算机科学 2025-09-16 Lianjun Liao , Chunhui Zhang , Tong Wu , Henglei Lv , Bailin Deng , Lin Gao

Recent advancements in multi-modal 3D pre-training methods have shown promising efficacy in learning joint representations of text, images, and point clouds. However, adopting point clouds as 3D representation fails to fully capture the…

计算机视觉与模式识别 · 计算机科学 2025-02-28 Haoyuan Li , Yanpeng Zhou , Tao Tang , Jifei Song , Yihan Zeng , Michael Kampffmeyer , Hang Xu , Xiaodan Liang

Reconstructing static 3D scene from monocular video with dynamic objects is important for numerous applications such as virtual reality and autonomous driving. Current approaches typically rely on background for static scene reconstruction,…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Yedong Shen , Shiqi Zhang , Sha Zhang , Yifan Duan , Xinran Zhang , Wenhao Yu , Lu Zhang , Jiajun Deng , Yanyong Zhang

With their meaningful geometry and their omnipresence in the 3D world, edges are extremely useful primitives in computer vision. 3D edges comprise of lines and curves, and methods to reconstruct them use either multi-view images or point…

计算机视觉与模式识别 · 计算机科学 2025-02-12 Kunal Chelani , Assia Benbihi , Torsten Sattler , Fredrik Kahl