中文
相关论文

相关论文: Self-Calibrating 4D Novel View Synthesis from Mono…

200 篇论文

3D Gaussian Splatting is emerging as a state-of-the-art technique in novel view synthesis, recognized for its impressive balance between visual quality, speed, and rendering efficiency. However, reliance on third-degree spherical harmonics…

计算机视觉与模式识别 · 计算机科学 2025-01-03 Yiwen Wang , Siyuan Chen , Ran Yi

We propose GS-IR, a novel inverse rendering approach based on 3D Gaussian Splatting (GS) that leverages forward mapping volume rendering to achieve photorealistic novel view synthesis and relighting results. Unlike previous works that use…

计算机视觉与模式识别 · 计算机科学 2024-03-29 Zhihao Liang , Qi Zhang , Ying Feng , Ying Shan , Kui Jia

The recent advancements in 3D Gaussian Splatting (3DGS) have demonstrated remarkable potential in novel view synthesis tasks. The divide-and-conquer paradigm has enabled large-scale scene reconstruction, but significant challenges remain in…

计算机视觉与模式识别 · 计算机科学 2025-04-16 Yongchang Wu , Zipeng Qi , Zhenwei Shi , Zhengxia Zou

3D Gaussian splatting enables high-quality novel view synthesis (NVS) at real-time frame rates. However, its quality drops sharply as we depart from the training views. Thus, dense captures are needed to match the high-quality expectations…

3D Gaussian Splatting (3DGS) has revolutionized neural rendering with its efficiency and quality, but like many novel view synthesis methods, it heavily depends on accurate camera poses from Structure-from-Motion (SfM) systems. Although…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Zhisheng Huang , Peng Wang , Jingdong Zhang , Yuan Liu , Xin Li , Wenping Wang

Given just a few glimpses of a scene, can you imagine the movie playing out as the camera glides through it? That's the lens we take on \emph{sparse-input novel view synthesis}, not only as filling spatial gaps between widely spaced views,…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Yan Xu , Yixing Wang , Stella X. Yu

Recently, Gaussian Splatting has sparked a new trend in the field of computer vision. Apart from novel view synthesis, it has also been extended to the area of multi-view reconstruction. The latest methods facilitate complete, detailed…

计算机视觉与模式识别 · 计算机科学 2025-01-09 Han Huang , Yulun Wu , Chao Deng , Ge Gao , Ming Gu , Yu-Shen Liu

Recently, 3D Gaussian Splatting has emerged as a prominent research direction owing to its ultrarapid training speed and high-fidelity rendering capabilities. However, the unstructured and irregular nature of Gaussian point clouds poses…

计算机视觉与模式识别 · 计算机科学 2026-02-16 Xiao Ren , Yu Liu , Ning An , Jian Cheng , Xin Qiao , He Kong

High dynamic range (HDR) novel view synthesis (NVS) aims to reconstruct HDR scenes by leveraging multi-view low dynamic range (LDR) images captured at different exposure levels. Current training paradigms with 3D tone mapping often result…

计算机视觉与模式识别 · 计算机科学 2025-03-14 Jinfeng Liu , Lingtong Kong , Bo Li , Dan Xu

In this paper, we present a self-calibrating framework that jointly optimizes camera parameters, lens distortion and 3D Gaussian representations, enabling accurate and efficient scene reconstruction. In particular, our technique enables…

计算机视觉与模式识别 · 计算机科学 2025-04-07 Youming Deng , Wenqi Xian , Guandao Yang , Leonidas Guibas , Gordon Wetzstein , Steve Marschner , Paul Debevec

Dynamic scene reconstruction from monocular video is essential for real-world applications. We introduce DGNS, a hybrid framework integrating \underline{D}eformable \underline{G}aussian Splatting and Dynamic \underline{N}eural…

计算机视觉与模式识别 · 计算机科学 2025-08-15 Xuesong Li , Jinguang Tong , Jie Hong , Vivien Rolland , Lars Petersson

3D Gaussian Splatting (3DGS) has emerged as a leading approach for high-quality novel view synthesis, with numerous variants extending its applicability to a broad spectrum of 3D and 4D scene reconstruction tasks. Despite its success, the…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Yiming Wang , Shaofei Wang , Marko Mihajlovic , Siyu Tang

3D Gaussian Splatting (3DGS) has shown significant advantages in novel view synthesis (NVS), particularly in achieving high rendering speeds and high-quality results. However, its geometric accuracy in 3D reconstruction remains limited due…

图形学 · 计算机科学 2025-02-21 Qilin Zhang , Olaf Wysocki , Steffen Urban , Boris Jutzi

Synthesizing consistent and photorealistic 3D scenes is an open problem in computer vision. Video diffusion models generate impressive videos but cannot directly synthesize 3D representations, i.e., lack 3D consistency in the generated…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Katja Schwarz , Norman Mueller , Peter Kontschieder

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

4D millimeter-wave radar is a promising sensing modality for autonomous driving, yet effective 3D object detection from 4D radar and monocular images remains challenging. Existing fusion approaches either rely on instance proposals lacking…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Xiaokai Bai , Chenxu Zhou , Lianqing Zheng , Si-Yuan Cao , Jianan Liu , Xiaohan Zhang , Yiming Li , Zhengzhuang Zhang , Hui-liang Shen

Synthesizing novel views from in-the-wild monocular videos is challenging due to scene dynamics and the lack of multi-view cues. To address this, we propose SplineGS, a COLMAP-free dynamic 3D Gaussian Splatting (3DGS) framework for…

计算机视觉与模式识别 · 计算机科学 2024-12-19 Jongmin Park , Minh-Quan Viet Bui , Juan Luis Gonzalez Bello , Jaeho Moon , Jihyong Oh , Munchurl Kim

3D Gaussian Splatting has recently achieved notable success in novel view synthesis for dynamic scenes and geometry reconstruction in static scenes. Building on these advancements, early methods have been developed for dynamic surface…

计算机视觉与模式识别 · 计算机科学 2024-11-12 Decai Chen , Brianne Oberson , Ingo Feldmann , Oliver Schreer , Anna Hilsmann , Peter Eisert

Recovering 3D information from scenes via multi-view stereo reconstruction (MVS) and novel view synthesis (NVS) is inherently challenging, particularly in scenarios involving sparse-view setups. The advent of 3D Gaussian Splatting (3DGS)…

计算机视觉与模式识别 · 计算机科学 2025-05-06 Shubhendu Jena , Shishir Reddy Vutukur , Adnane Boukhayma

This paper proposes a novel framework for large-scale scene reconstruction based on 3D Gaussian splatting (3DGS) and aims to address the scalability and accuracy challenges faced by existing methods. For tackling the scalability issue, we…

计算机视觉与模式识别 · 计算机科学 2024-09-25 Hanyue Zhang , Zhiliu Yang , Xinhe Zuo , Yuxin Tong , Ying Long , Chen Liu