Benchmarking robustness in neural radiance fields
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 …
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 …
scene representation and rendering. These data-driven models can learn to synthesize high …
NeRFail: Neural Radiance Fields-Based Multiview Adversarial Attack
Adversarial attacks,\ie generating adversarial perturbations with a small magnitude to
deceive deep neural networks, are important for investigating and improving model …
deceive deep neural networks, are important for investigating and improving model …
Poison-splat: Computation Cost Attack on 3D Gaussian Splatting
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 …
has become a dominant 3D representation and brought progress to many 3D vision tasks …
IPA-NeRF: Illusory Poisoning Attack Against Neural Radiance Fields
Abstract Neural Radiance Field (NeRF) represents a significant advancement in computer
vision, offering implicit neural network-based scene representation and novel view synthesis …
vision, offering implicit neural network-based scene representation and novel view synthesis …