Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations

• URL: http://arxiv.org/abs/2309.13150v2
• Date: Sun, 3 Mar 2024 02:54:34 GMT
• Title: Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations
• Authors: Hanjiang Hu, Zuxin Liu, Linyi Li, Jiacheng Zhu, Ding Zhao
• Abstract summary: We present a framework for certifying the robustness of 3D-2D projective transformations against camera motion perturbations. Our approach leverages a smoothing distribution over the 2D pixel space instead of in the 3D physical space. Our approach achieves approximately 80% certified accuracy while utilizing only 30% of the projected image frames.
• Score: 45.576866560987405
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Deep learning-based visual perception models lack robustness when faced with camera motion perturbations in practice. The current certification process for assessing robustness is costly and time-consuming due to the extensive number of image projections required for Monte Carlo sampling in the 3D camera motion space. To address these challenges, we present a novel, efficient, and practical framework for certifying the robustness of 3D-2D projective transformations against camera motion perturbations. Our approach leverages a smoothing distribution over the 2D pixel space instead of in the 3D physical space, eliminating the need for costly camera motion sampling and significantly enhancing the efficiency of robustness certifications. With the pixel-wise smoothed classifier, we are able to fully upper bound the projection errors using a technique of uniform partitioning in camera motion space. Additionally, we extend our certification framework to a more general scenario where only a single-frame point cloud is required in the projection oracle. Through extensive experimentation, we validate the trade-off between effectiveness and efficiency enabled by our proposed method. Remarkably, our approach achieves approximately 80% certified accuracy while utilizing only 30% of the projected image frames. The code is available at https://github.com/HanjiangHu/pixel-wise-smoothing.

Related papers

• Neural Real-Time Recalibration for Infrared Multi-Camera Systems [2.249916681499244]
  There are no learning-free or neural techniques for real-time recalibration of infrared multi-camera systems. We propose a neural network-based method capable of dynamic real-time calibration.
  arXiv  Detail & Related papers  (2024-10-18T14:37:37Z)
• SpatialTracker: Tracking Any 2D Pixels in 3D Space [71.58016288648447]
  We propose to estimate point trajectories in 3D space to mitigate the issues caused by image projection. Our method, named SpatialTracker, lifts 2D pixels to 3D using monocular depth estimators. Tracking in 3D allows us to leverage as-rigid-as-possible (ARAP) constraints while simultaneously learning a rigidity embedding that clusters pixels into different rigid parts.
  arXiv  Detail & Related papers  (2024-04-05T17:59:25Z)
• VICAN: Very Efficient Calibration Algorithm for Large Camera Networks [49.17165360280794]
  We introduce a novel methodology that extends Pose Graph Optimization techniques. We consider the bipartite graph encompassing cameras, object poses evolving dynamically, and camera-object relative transformations at each time step. Our framework retains compatibility with traditional PGO solvers, but its efficacy benefits from a custom-tailored optimization scheme.
  arXiv  Detail & Related papers  (2024-03-25T17:47:03Z)
• Joint 3D Shape and Motion Estimation from Rolling Shutter Light-Field Images [2.0277446818410994]
  We propose an approach to address the problem of 3D reconstruction of scenes from a single image captured by a light-field camera equipped with a rolling shutter sensor. Our method leverages the 3D information cues present in the light-field and the motion information provided by the rolling shutter effect. We present a generic model for the imaging process of this sensor and a two-stage algorithm that minimizes the re-projection error.
  arXiv  Detail & Related papers  (2023-11-02T15:08:18Z)
• Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction [54.00007868515432]
  Existing methods face challenges in estimating the accurate correction field due to the uniform velocity assumption. We propose a geometry-based Quadratic Rolling Shutter (QRS) motion solver, which precisely estimates the high-order correction field of individual pixels. Our method surpasses the state-of-the-art by +4.98, +0.77, and +4.33 of PSNR on Carla-RS, Fastec-RS, and BS-RSC datasets, respectively.
  arXiv  Detail & Related papers  (2023-03-31T15:09:18Z)
• Robustness Certification of Visual Perception Models via Camera Motion Smoothing [23.5329905995857]
  We study the robustness of the visual perception model under camera motion perturbations to investigate the influence of camera motion on robotic perception. We propose a motion smoothing technique for arbitrary image classification models, whose robustness under camera motion perturbations could be certified. We conduct extensive experiments to validate the certification approach via motion smoothing against camera motion perturbations.
  arXiv  Detail & Related papers  (2022-10-04T15:31:57Z)
• Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred Objects in Videos [115.71874459429381]
  We propose a method for jointly estimating the 3D motion, 3D shape, and appearance of highly motion-blurred objects from a video. Experiments on benchmark datasets demonstrate that our method outperforms previous methods for fast moving object deblurring and 3D reconstruction.
  arXiv  Detail & Related papers  (2021-11-29T11:25:14Z)
• Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation [57.11299763566534]
  We present a solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. We exploit 3D geometry to fuse input images into a unified latent representation of pose, which is disentangled from camera view-points. Our architecture then conditions the learned representation on camera projection operators to produce accurate per-view 2d detections.
  arXiv  Detail & Related papers  (2020-04-05T12:52:29Z)
• Learning Precise 3D Manipulation from Multiple Uncalibrated Cameras [13.24490469380487]
  We present an effective multi-view approach to end-to-end learning of precise manipulation tasks that are 3D in nature. Our method learns to accomplish these tasks using multiple statically placed but uncalibrated RGB camera views without building an explicit 3D representation such as a pointcloud or voxel grid.
  arXiv  Detail & Related papers  (2020-02-21T03:28:42Z)

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.