中文
相关论文

相关论文: EGGS: Exchangeable 2D/3D Gaussian Splatting for Ge…

200 篇论文

We present an efficient neural 3D scene representation for novel-view synthesis (NVS) in large-scale, dynamic urban areas. Existing works are not well suited for applications like mixed-reality or closed-loop simulation due to their limited…

计算机视觉与模式识别 · 计算机科学 2024-11-26 Tobias Fischer , Jonas Kulhanek , Samuel Rota Bulò , Lorenzo Porzi , Marc Pollefeys , Peter Kontschieder

3D Gaussian Splatting (3DGS) has emerged as a powerful technique for real-time LiDAR and camera synthesis in autonomous driving simulation. However, simulating LiDAR with 3DGS remains challenging for extrapolated views beyond the training…

机器人学 · 计算机科学 2026-03-17 Yiming Huang , Xin Kang , Sipeng Zhang , Hongliang Ren , Weihua Zhang , Junjie Lai

We present the first systematic comparison of implicit and explicit Novel View Synthesis methods for space-based 3D object reconstruction, evaluating the role of appearance embeddings. While embeddings improve photometric fidelity by…

计算机视觉与模式识别 · 计算机科学 2025-09-16 Elias De Smijter , Renaud Detry , Christophe De Vleeschouwer

One of the key advantages of 3D rendering is its ability to simulate intricate scenes accurately. One of the most widely used methods for this purpose is Gaussian Splatting, a novel approach that is known for its rapid training and…

图形学 · 计算机科学 2024-05-31 Artur Kasymov , Bartosz Czekaj , Marcin Mazur , Jacek Tabor , Przemysław Spurek

Novel view synthesis (NVS) in low-light scenes remains a significant challenge due to degraded inputs characterized by severe noise, low dynamic range (LDR) and unreliable initialization. While recent NeRF-based approaches have shown…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Hao Sun , Fenggen Yu , Huiyao Xu , Tao Zhang , Changqing Zou

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

In the rapidly evolving field of 3D reconstruction, 3D Gaussian Splatting (3DGS) and 2D Gaussian Splatting (2DGS) represent significant advancements. Although 2DGS compresses 3D Gaussian primitives into 2D Gaussian surfels to effectively…

计算机视觉与模式识别 · 计算机科学 2024-07-17 Zhuoxiao Li , Shanliang Yao , Yijie Chu , Angel F. Garcia-Fernandez , Yong Yue , Eng Gee Lim , Xiaohui Zhu

Following the advent of NeRFs, 3D Gaussian Splatting (3D-GS) has paved the way to real-time neural rendering overcoming the computational burden of volumetric methods. Following the pioneering work of 3D-GS, several methods have attempted…

计算机视觉与模式识别 · 计算机科学 2024-05-01 Evangelos Ververas , Rolandos Alexandros Potamias , Jifei Song , Jiankang Deng , Stefanos Zafeiriou

This paper describes the Qualcomm AI Research solution to the RealADSim-NVS challenge, hosted at the RealADSim Workshop at ICCV 2025. The challenge concerns novel view synthesis in street scenes, and participants are required to generate,…

计算机视觉与模式识别 · 计算机科学 2025-10-15 Mohamed Omran , Farhad Zanjani , Davide Abati , Jens Petersen , Amirhossein Habibian

The introduction of 3D Gaussian Splatting (3DGS) has advanced novel view synthesis by utilizing Gaussians to represent scenes. Encoding Gaussian point features with anchor embeddings has significantly enhanced the performance of newer 3DGS…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Junyan Su , Baozhu Zhao , Xiaohan Zhang , Qi Liu

This paper presents Planar Gaussian Splatting (PGS), a novel neural rendering approach to learn the 3D geometry and parse the 3D planes of a scene, directly from multiple RGB images. The PGS leverages Gaussian primitives to model the scene…

计算机视觉与模式识别 · 计算机科学 2024-12-04 Farhad G. Zanjani , Hong Cai , Hanno Ackermann , Leila Mirvakhabova , Fatih Porikli

3D Gaussian Splatting (3DGS) has demonstrated impressive capabilities in novel view synthesis. However, rendering reflective objects remains a significant challenge, particularly in inverse rendering and relighting. We introduce RTR-GS, a…

图形学 · 计算机科学 2025-12-17 Yongyang Zhou , Fang-Lue Zhang , Zichen Wang , Lei Zhang

Recent advancements in 3D editing have highlighted the potential of text-driven methods in real-time, user-friendly AR/VR applications. However, current methods rely on 2D diffusion models without adequately considering multi-view…

计算机视觉与模式识别 · 计算机科学 2025-04-21 Dong In Lee , Hyeongcheol Park , Jiyoung Seo , Eunbyung Park , Hyunje Park , Ha Dam Baek , Sangheon Shin , Sangmin Kim , Sangpil Kim

Generalizable Gaussian Splatting aims to synthesize novel views for unseen scenes without per-scene optimization. In particular, recent advancements utilize feed-forward networks to predict per-pixel Gaussian parameters, enabling…

计算机视觉与模式识别 · 计算机科学 2025-08-29 Yuxi Hu , Jun Zhang , Kuangyi Chen , Zhe Zhang , Friedrich Fraundorfer

3D Gaussians have recently emerged as an effective scene representation for real-time splatting and accurate novel-view synthesis, motivating several works to adapt multi-view structure prediction networks to regress per-pixel 3D Gaussians…

计算机视觉与模式识别 · 计算机科学 2025-12-22 Mehdi Hosseinzadeh , Shin-Fang Chng , Yi Xu , Simon Lucey , Ian Reid , Ravi Garg

While 3D Gaussian splatting (3DGS) offers explicit and efficient scene representations for cone-beam computed tomography reconstruction, conventional photometric optimization inherently suffers from spectral bias under ultra sparse-view…

计算机视觉与模式识别 · 计算机科学 2026-05-01 Jian Lin , Jiancheng Fang , Shaoyu Wang , Changan Lai , Yikun Zhang , Yang Chen , Qiegen Liu

Recent breakthroughs in radiance fields have significantly advanced 3D scene reconstruction and novel view synthesis (NVS) in autonomous driving. Nevertheless, critical limitations persist: reconstruction-based methods exhibit substantial…

计算机视觉与模式识别 · 计算机科学 2025-03-14 Yingshuang Zou , Yikang Ding , Chuanrui Zhang , Jiazhe Guo , Bohan Li , Xiaoyang Lyu , Feiyang Tan , Xiaojuan Qi , Haoqian Wang

3D Gaussian Splatting reconstructs scenes by starting from a sparse Structure-from-Motion initialization and refining under-reconstructed regions. This process is slow, as it requires multiple densification steps where Gaussians are…

图形学 · 计算机科学 2026-02-13 Dmytro Kotovenko , Olga Grebenkova , Björn Ommer

Recently, 3D Gaussian Splatting (3DGS) has revolutionized radiance field reconstruction, manifesting efficient and high-fidelity novel view synthesis. However, accurately representing surfaces, especially in large and complex scenarios,…

计算机视觉与模式识别 · 计算机科学 2025-03-05 Yang Liu , Chuanchen Luo , Zhongkai Mao , Junran Peng , Zhaoxiang Zhang

3D Gaussian Splatting (3DGS) has recently emerged as a pioneering approach in explicit scene rendering and computer graphics. Unlike traditional neural radiance field (NeRF) methods, which typically rely on implicit, coordinate-based models…