Benchmarking robustness in neural radiance fields

C Wang, A Wang, J Li, A Yuille… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Abstract Neural Radiance Field (NeRF) has demonstrated excellent quality in novel view
synthesis thanks to its ability to model 3D object geometries in a concise formulation …

Targeted Adversarial Attacks on Generalizable Neural Radiance Fields

A Horváth, CM Józsa - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Abstract Neural Radiance Fields (NeRFs) have recently emerged as a powerful tool for 3D
scene representation and rendering. These data-driven models can learn to synthesize high …

NeRFail: Neural Radiance Fields-Based Multiview Adversarial Attack

W Jiang, H Zhang, X Wang, Z Guo… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Adversarial attacks,\ie generating adversarial perturbations with a small magnitude to
deceive deep neural networks, are important for investigating and improving model …

Poison-splat: Computation Cost Attack on 3D Gaussian Splatting

J Lu, Y Zhang, Q Shen, X Wang, S Yan - arXiv preprint arXiv:2410.08190, 2024 - arxiv.org
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 …

IPA-NeRF: Illusory Poisoning Attack Against Neural Radiance Fields

W Jiang, H Zhang, S Zhao, Z Guo, H Wang - ECAI 2024, 2024 - ebooks.iospress.nl
Abstract Neural Radiance Field (NeRF) represents a significant advancement in computer
vision, offering implicit neural network-based scene representation and novel view synthesis …