UV-Attack: Physical-World Adversarial Attacks for Person Detection via Dynamic-NeRF-based UV Mapping

• URL: http://arxiv.org/abs/2501.05783v1
• Date: Fri, 10 Jan 2025 08:33:31 GMT
• Title: UV-Attack: Physical-World Adversarial Attacks for Person Detection via Dynamic-NeRF-based UV Mapping
• Abstract summary: adversarial attacks on person detectors have struggled with low success rates due to the flexible nature of human movement.<n>We introduce UV-Attack, a groundbreaking approach that achieves high success rates even with extensive and unseen human actions.
• Score: 27.142039594420293
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent research, adversarial attacks on person detectors using patches or static 3D model-based texture modifications have struggled with low success rates due to the flexible nature of human movement. Modeling the 3D deformations caused by various actions has been a major challenge. Fortunately, advancements in Neural Radiance Fields (NeRF) for dynamic human modeling offer new possibilities. In this paper, we introduce UV-Attack, a groundbreaking approach that achieves high success rates even with extensive and unseen human actions. We address the challenge above by leveraging dynamic-NeRF-based UV mapping. UV-Attack can generate human images across diverse actions and viewpoints, and even create novel actions by sampling from the SMPL parameter space. While dynamic NeRF models are capable of modeling human bodies, modifying clothing textures is challenging because they are embedded in neural network parameters. To tackle this, UV-Attack generates UV maps instead of RGB images and modifies the texture stacks. This approach enables real-time texture edits and makes the attack more practical. We also propose a novel Expectation over Pose Transformation loss (EoPT) to improve the evasion success rate on unseen poses and views. Our experiments show that UV-Attack achieves a 92.75% attack success rate against the FastRCNN model across varied poses in dynamic video settings, significantly outperforming the state-of-the-art AdvCamou attack, which only had a 28.50% ASR. Moreover, we achieve 49.5% ASR on the latest YOLOv8 detector in black-box settings. This work highlights the potential of dynamic NeRF-based UV mapping for creating more effective adversarial attacks on person detectors, addressing key challenges in modeling human movement and texture modification.

Related papers

• Generative Relightable Avatars [54.38436795769187]
  Generative Relightable Avatars (GRA) is a person-specific method for free-view rendering and environment-map relighting of full-body humans.<n>GRA follows a hybrid approach that combines controllable, physics-grounded relighting with probabilistic refinement.
  arXiv  Detail & Related papers  (2026-06-21T23:36:00Z)
• Dy3DGS-SLAM: Monocular 3D Gaussian Splatting SLAM for Dynamic Environments [5.050525952210101]
  We propose Dy3DGS-SLAM, the first 3D Gaussian Splatting (3DGS) SLAM method for dynamic scenes using monocular RGB input.<n>Results demonstrate that Dy3DGS-SLAM achieves state-of-the-art tracking and rendering in dynamic environments.
  arXiv  Detail & Related papers  (2025-06-06T10:43:41Z)
• UVMap-ID: A Controllable and Personalized UV Map Generative Model [67.71022515856653]
  We introduce UVMap-ID, a controllable and personalized UV Map generative model. Unlike traditional large-scale training methods in 2D, we propose to fine-tune a pre-trained text-to-image diffusion model. Both quantitative and qualitative analyses demonstrate the effectiveness of our method in controllable and personalized UV Map generation.
  arXiv  Detail & Related papers  (2024-04-22T20:30:45Z)
• Taming Latent Diffusion Model for Neural Radiance Field Inpainting [63.297262813285265]
  Neural Radiance Field (NeRF) is a representation for 3D reconstruction from multi-view images. We propose tempering the diffusion model'sity with per-scene customization and mitigating the textural shift with masked training. Our framework yields state-of-the-art NeRF inpainting results on various real-world scenes.
  arXiv  Detail & Related papers  (2024-04-15T17:59:57Z)
• UV Gaussians: Joint Learning of Mesh Deformation and Gaussian Textures for Human Avatar Modeling [71.87807614875497]
  We propose UV Gaussians, which models the 3D human body by jointly learning mesh deformations and 2D UV-space Gaussian textures. We collect and process a new dataset of human motion, which includes multi-view images, scanned models, parametric model registration, and corresponding texture maps. Experimental results demonstrate that our method achieves state-of-the-art synthesis of novel view and novel pose.
  arXiv  Detail & Related papers  (2024-03-18T09:03:56Z)
• Animating NeRFs from Texture Space: A Framework for Pose-Dependent Rendering of Human Performances [11.604386285817302]
  We introduce a novel NeRF-based framework for pose-dependent rendering of human performances. Our approach results in high-quality renderings for novel-view and novel-pose synthesis.
  arXiv  Detail & Related papers  (2023-11-06T14:34:36Z)
• MoDA: Modeling Deformable 3D Objects from Casual Videos [84.29654142118018]
  We propose neural dual quaternion blend skinning (NeuDBS) to achieve 3D point deformation without skin-collapsing artifacts. In the endeavor to register 2D pixels across different frames, we establish a correspondence between canonical feature embeddings that encodes 3D points within the canonical space. Our approach can reconstruct 3D models for humans and animals with better qualitative and quantitative performance than state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-04-17T13:49:04Z)
• NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects [63.04781030984006]
  Dynamic Neural Radiance Field (NeRF) is a powerful algorithm capable of rendering photo-realistic novel view images from a monocular RGB video of a dynamic scene. We address the limitation by reformulating the neural radiance field function to be conditioned on surface position and orientation in the observation space. We evaluate our model based on the novel view synthesis quality with a self-collected dataset of different moving specular objects in realistic environments.
  arXiv  Detail & Related papers  (2023-03-25T11:03:53Z)
• Controllable Radiance Fields for Dynamic Face Synthesis [125.48602100893845]
  We study how to explicitly control generative model synthesis of face dynamics exhibiting non-rigid motion. Controllable Radiance Field (CoRF) On head image/video data we show that CoRFs are 3D-aware while enabling editing of identity, viewing directions, and motion.
  arXiv  Detail & Related papers  (2022-10-11T23:17:31Z)
• Learning Dynamic View Synthesis With Few RGBD Cameras [60.36357774688289]
  We propose to utilize RGBD cameras to synthesize free-viewpoint videos of dynamic indoor scenes. We generate point clouds from RGBD frames and then render them into free-viewpoint videos via a neural feature. We introduce a simple Regional Depth-Inpainting module that adaptively inpaints missing depth values to render complete novel views.
  arXiv  Detail & Related papers  (2022-04-22T03:17:35Z)
• UV Volumes for Real-time Rendering of Editable Free-view Human Performance [35.089358945669865]
  UV Volumes is an approach that can render an editable free-view video of a human performer in real-time. It is achieved by removing the high-frequency (i.e., non-smooth) human textures from the 3D volume and encoding them into a 2D neural texture stack. Experiments on CMU Panoptic, ZJU Mocap, and H36M datasets show that our model can render 900 * 500 images in 40 fps.
  arXiv  Detail & Related papers  (2022-03-27T21:54:36Z)
• HVTR: Hybrid Volumetric-Textural Rendering for Human Avatars [65.82222842213577]
  We propose a novel neural rendering pipeline, which synthesizes virtual human avatars from arbitrary poses efficiently and at high quality. First, we learn to encode articulated human motions on a dense UV manifold of the human body surface. We then leverage the encoded information on the UV manifold to construct a 3D volumetric representation.
  arXiv  Detail & Related papers  (2021-12-19T17:34:15Z)
• StyleUV: Diverse and High-fidelity UV Map Generative Model [24.982824840625216]
  We present a novel UV map generative model that learns to generate diverse and realistic synthetic UV maps without requiring high-quality UV maps for training. Both quantitative and qualitative evaluations demonstrate that our proposed texture model produces more diverse and higher fidelity textures compared to existing methods.
  arXiv  Detail & Related papers  (2020-11-25T17:19:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.