中文
相关论文

相关论文: GaussTrap: Stealthy Poisoning Attacks on 3D Gaussi…

200 篇论文

3D scene representation methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have significantly advanced novel view synthesis. As these methods become prevalent, addressing their vulnerabilities becomes critical. We…

计算机视觉与模式识别 · 计算机科学 2025-10-03 Bo-Hsu Ke , You-Zhe Xie , Yu-Lun Liu , Wei-Chen Chiu

With 3D Gaussian Splatting (3DGS) being increasingly used in safety-critical applications, how can an adversary manipulate the scene to cause harm? We introduce CLOAK, the first attack that leverages view-dependent Gaussian appearances -…

As 3D Gaussian Splatting (3DGS) gains rapid adoption in safety-critical tasks for efficient novel-view synthesis from static images, how might an adversary tamper images to cause harm? We introduce ComplicitSplat, the first attack that…

计算机视觉与模式识别 · 计算机科学 2025-09-09 Matthew Hull , Haoyang Yang , Pratham Mehta , Mansi Phute , Aeree Cho , Haorang Wang , Matthew Lau , Wenke Lee , Wilian Lunardi , Martin Andreoni , Duen Horng Chau

3D Gaussian splatting (3DGS), known for its groundbreaking performance and efficiency, has become a dominant 3D representation and brought progress to many 3D vision tasks. However, in this work, we reveal a significant security…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Jiahao Lu , Yifan Zhang , Qiuhong Shen , Xinchao Wang , Shuicheng Yan

3D Gaussian Splatting (3DGS) is increasingly recognized as a powerful paradigm for real-time, high-fidelity 3D reconstruction. However, its per-scene optimization pipeline limits scalability and generalization, and prevents efficient…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Yiran Qiao , Yiren Lu , Yunlai Zhou , Rui Yang , Linlin Hou , Yu Yin , Jing Ma

Three-dimensional Gaussian Splatting (3DGS) has recently emerged as an efficient representation for novel-view synthesis, achieving impressive visual quality. However, in scenes dominated by large and low-texture regions, common in indoor…

计算机视觉与模式识别 · 计算机科学 2025-10-29 Xirui Jin , Renbiao Jin , Boying Li , Danping Zou , Wenxian Yu

We propose a method to enhance 3D Gaussian Splatting (3DGS)~\cite{Kerbl2023}, addressing challenges in initialization, optimization, and density control. Gaussian Splatting is an alternative for rendering realistic images while supporting…

计算机视觉与模式识别 · 计算机科学 2025-07-02 Xingjun Wang , Lianlei Shan

3D Gaussian Splatting (3DGS) has recently enabled real-time rendering of unbounded 3D scenes for novel view synthesis. However, this technique requires dense training views to accurately reconstruct 3D geometry. A limited number of input…

计算机视觉与模式识别 · 计算机科学 2025-03-28 Haolin Xiong , Sairisheek Muttukuru , Rishi Upadhyay , Pradyumna Chari , Achuta Kadambi

3D Gaussian Splatting (3DGS) has recently enabled highly photorealistic 3D reconstruction from casually captured multi-view images. However, this accessibility raises a privacy concern: publicly available images or videos can be exploited…

计算机视觉与模式识别 · 计算机科学 2026-04-16 Prajas Wadekar , Venkata Sai Pranav Bachina , Kunal Bhosikar , Ankit Gangwal , Charu Sharma

3D Gaussian Splatting (3DGS) is a recent approach for scene rendering. Although primarily designed for view synthesis, its potential for scene understanding tasks remains underexplored. In this work, we conduct a comparative evaluation of…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Julia Farganus , Krzysztof Żurawicki , Arkadiusz Gaweł , Weronika Jakubowska , Halina Kwaśnicka

3D Gaussian Splatting (3DGS) has emerged as a powerful paradigm for real-time and high-fidelity 3D reconstruction from posed images. However, recent studies reveal its vulnerability to adversarial corruptions in input views, where…

计算机视觉与模式识别 · 计算机科学 2026-02-24 Yiran Qiao , Yiren Lu , Yunlai Zhou , Rui Yang , Linlin Hou , Yu Yin , Jing Ma

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

3D Gaussian Splatting has advanced radiance field reconstruction, enabling high-quality view synthesis and fast rendering in 3D modeling. While adversarial attacks on object detection models are well-studied for 2D images, their impact on…

计算机视觉与模式识别 · 计算机科学 2024-12-05 Abdurrahman Zeybey , Mehmet Ergezer , Tommy Nguyen

The problem of 3D reconstruction from posed images is undergoing a fundamental transformation, driven by continuous advances in 3D Gaussian Splatting (3DGS). By modeling scenes explicitly as collections of 3D Gaussians, 3DGS enables…

计算机视觉与模式识别 · 计算机科学 2026-03-02 Vitor Pereira Matias , Daniel Perazzo , Vinicius Silva , Alberto Raposo , Luiz Velho , Afonso Paiva , Tiago Novello

Recent advances in 3D Gaussian Splatting (3DGS) deliver high-quality rendering, yet the Gaussian representation exposes a new attack surface, the resource-targeting attack. This attack poisons training images, excessively inducing Gaussian…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Yang Chen , Yi Yu , Jiaming He , Yueqi Duan , Zheng Zhu , Yap-Peng Tan

As a mainstream technique for 3D reconstruction, 3D Gaussian splatting (3DGS) has been applied in a wide range of applications and services. Recent studies have revealed critical vulnerabilities in this pipeline and introduced computation…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Yanping Li , Zhening Liu , Zijian Li , Zehong Lin , Jun Zhang

Recent advances in 3D reconstruction and neural rendering,particularly 3D Gaussian Splatting, make it feasible and simple to edit 3D scenes and re-render them as highly realistic images. Therefore, security concerns arise regarding the…

计算机视觉与模式识别 · 计算机科学 2026-05-01 Davide Di Nucci , Riccardo Catalini , Guido Borghi , Roberto Vezzani

Recent advancements in 3D Gaussian Splatting (3D-GS) have established new benchmarks for rendering quality and efficiency in 3D reconstruction. However, 3D-GS faces critical limitations when generating novel views that significantly deviate…

图形学 · 计算机科学 2025-03-05 Yifei Gao , Kerui Ren , Jie Ou , Lei Wang , Jiaji Wu , Jun Cheng

Backdoor attacks implant hidden behaviors into models by poisoning training data or modifying the model directly. These attacks aim to maintain high accuracy on benign inputs while causing misclassification when a specific trigger is…

密码学与安全 · 计算机科学 2025-12-10 Jianyao Yin , Luca Arnaboldi , Honglong Chen , Pascal Berrang , Mark Ryan

Recent advancements in 3D Gaussian Splatting(3DGS) have significantly improved semantic scene understanding, enabling natural language queries to localize objects within a scene. However, existing methods primarily focus on embedding…

计算机视觉与模式识别 · 计算机科学 2025-03-07 Xihan Wang , Dianyi Yang , Yu Gao , Yufeng Yue , Yi Yang , Mengyin Fu
‹ 上一页 1 2 3 10 下一页 ›