中文
相关论文

相关论文: GaussianDiffusion: 3D Gaussian Splatting for Denoi…

200 篇论文

Gaussian Splatting has emerged as a prominent model for constructing 3D representations from images across diverse domains. However, the efficiency of the 3D Gaussian Splatting rendering pipeline relies on several simplifications. Notably,…

3D Gaussian Splatting (3DGS) has transformed novel-view synthesis with its fast, interpretable, and high-fidelity rendering. However, its resource requirements limit its usability. Especially on constrained devices, training performance…

计算机视觉与模式识别 · 计算机科学 2024-06-25 Saswat Subhajyoti Mallick , Rahul Goel , Bernhard Kerbl , Francisco Vicente Carrasco , Markus Steinberger , Fernando De La Torre

3D Gaussian Splatting (3DGS) proposes an efficient solution for novel view synthesis. Its framework provides fast and high-fidelity rendering. Although less complex than other solutions such as Neural Radiance Fields (NeRF), there are still…

计算机视觉与模式识别 · 计算机科学 2025-04-03 Stéphane Pateux , Matthieu Gendrin , Luce Morin , Théo Ladune , Xiaoran Jiang

3D Gaussian Splatting (3DGS) is a new method for modeling and rendering 3D radiance fields that achieves much faster learning and rendering time compared to SOTA NeRF methods. However, it comes with a drawback in the much larger storage…

计算机视觉与模式识别 · 计算机科学 2024-09-30 KL Navaneet , Kossar Pourahmadi Meibodi , Soroush Abbasi Koohpayegani , Hamed Pirsiavash

The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Peizhen Zheng , Dongjing Jiang , Qingchong Jiao , Redouane EL Bouchtaoui , Flynnwell Jianfei Zhang

We introduce a method for using event camera data in novel view synthesis via Gaussian Splatting. Event cameras offer exceptional temporal resolution and a high dynamic range. Leveraging these capabilities allows us to effectively address…

计算机视觉与模式识别 · 计算机科学 2025-05-22 Toshiya Yura , Ashkan Mirzaei , Igor Gilitschenski

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…

计算机视觉与模式识别 · 计算机科学 2025-11-20 Junseo Koo , Jinseo Jeong , Gunhee Kim

Generating and inserting new objects into 3D content is a compelling approach for achieving versatile scene recreation. Existing methods, which rely on SDS optimization or single-view inpainting, often struggle to produce high-quality…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Hongliang Zhong , Can Wang , Jingbo Zhang , Jing Liao

The emergence of 3D Gaussian Splatting (3D-GS) has significantly advanced 3D reconstruction by providing high fidelity and fast training speeds across various scenarios. While recent efforts have mainly focused on improving model structures…

图形学 · 计算机科学 2025-03-07 Yifei Gao , Jun Huang , Lei Wang , Ruiting Dai , Jun Cheng

We present DreamPolisher, a novel Gaussian Splatting based method with geometric guidance, tailored to learn cross-view consistency and intricate detail from textual descriptions. While recent progress on text-to-3D generation methods have…

计算机视觉与模式识别 · 计算机科学 2024-03-27 Yuanze Lin , Ronald Clark , Philip Torr

3D city generation with NeRF-based methods shows promising generation results but is computationally inefficient. Recently 3D Gaussian Splatting (3D-GS) has emerged as a highly efficient alternative for object-level 3D generation. However,…

计算机视觉与模式识别 · 计算机科学 2025-02-28 Haozhe Xie , Zhaoxi Chen , Fangzhou Hong , Ziwei Liu

In recent years, Neural Radiance Fields (NeRF) has revolutionized three-dimensional (3D) reconstruction with its implicit representation. Building upon NeRF, 3D Gaussian Splatting (3D-GS) has departed from the implicit representation of…

计算机视觉与模式识别 · 计算机科学 2024-05-29 Bin Zhang , Bi Zeng , Zexin Peng

3D Gaussian Splatting is a novel method for 3D view synthesis, which can gain an implicit neural learning rendering result than the traditional neural rendering technology but keep the more high-definition fast rendering speed. But it is…

计算机视觉与模式识别 · 计算机科学 2024-05-13 Jinwei Lin

Neural Radiance Fields (NeRF) have been adapted for indoor 3D Object Detection (3DOD), offering a promising approach to indoor 3DOD via view-synthesis representation. But its implicit nature limits representational capacity. Recently, 3D…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Yang Cao , Yuanliang Ju , Dan Xu

Although 3D Gaussian Splatting (3D-GS) achieves efficient rendering for novel view synthesis, extending it to dynamic scenes still results in substantial memory overhead from replicating Gaussians across frames. To address this challenge,…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Chun-Tin Wu , Jun-Cheng Chen

The field of text-to-3D content generation has made significant progress in generating realistic 3D objects, with existing methodologies like Score Distillation Sampling (SDS) offering promising guidance. However, these methods often…

计算机视觉与模式识别 · 计算机科学 2024-09-11 Phu Pham , Aradhya N. Mathur , Ojaswa Sharma , Aniket Bera

3D Gaussian Splatting (3DGS) techniques have achieved satisfactory 3D scene representation. Despite their impressive performance, they confront challenges due to the limitation of structure-from-motion (SfM) methods on acquiring accurate…

计算机视觉与模式识别 · 计算机科学 2025-01-28 Ao Gao , Luosong Guo , Tao Chen , Zhao Wang , Ying Tai , Jian Yang , Zhenyu Zhang

Novel view synthesis of dynamic scenes has been an intriguing yet challenging problem. Despite recent advancements, simultaneously achieving high-resolution photorealistic results, real-time rendering, and compact storage remains a…

计算机视觉与模式识别 · 计算机科学 2024-04-08 Zhan Li , Zhang Chen , Zhong Li , Yi Xu

3D Gaussian Splatting represents a breakthrough in the field of novel view synthesis. It establishes Gaussians as core rendering primitives for highly accurate real-world environment reconstruction. Recent advances have drastically…

图形学 · 计算机科学 2025-06-25 Jonathan Haberl , Philipp Fleck , Clemens Arth

Novel View Synthesis (NVS) for street scenes play a critical role in the autonomous driving simulation. The current mainstream technique to achieve it is neural rendering, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting…

计算机视觉与模式识别 · 计算机科学 2024-04-01 Zhongrui Yu , Haoran Wang , Jinze Yang , Hanzhang Wang , Zeke Xie , Yunfeng Cai , Jiale Cao , Zhong Ji , Mingming Sun