Physically-admissible polarimetric data augmentation for road-scene analysis

• URL: http://arxiv.org/abs/2206.07431v1
• Date: Wed, 15 Jun 2022 10:04:43 GMT
• Title: Physically-admissible polarimetric data augmentation for road-scene analysis
• Authors: Cyprien Ruffino, Rachel Blin, Samia Ainouz, Gilles Gasso, Romain H\'erault, Fabrice Meriaudeau, St\'ephane Canu
• Abstract summary: We propose CycleGAN to transfer large labeled road scene datasets to the polarimetric domain. The resulting constrained CycleGAN is publicly released, allowing anyone to generate their own polarimetric images.
• Score: 4.972086627584208
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Polarimetric imaging, along with deep learning, has shown improved performances on different tasks including scene analysis. However, its robustness may be questioned because of the small size of the training datasets. Though the issue could be solved by data augmentation, polarization modalities are subject to physical feasibility constraints unaddressed by classical data augmentation techniques. To address this issue, we propose to use CycleGAN, an image translation technique based on deep generative models that solely relies on unpaired data, to transfer large labeled road scene datasets to the polarimetric domain. We design several auxiliary loss terms that, alongside the CycleGAN losses, deal with the physical constraints of polarimetric images. The efficiency of this solution is demonstrated on road scene object detection tasks where generated realistic polarimetric images allow to improve performances on cars and pedestrian detection up to 9%. The resulting constrained CycleGAN is publicly released, allowing anyone to generate their own polarimetric images.

Related papers

• Robust Depth Enhancement via Polarization Prompt Fusion Tuning [112.88371907047396]
  We present a framework that leverages polarization imaging to improve inaccurate depth measurements from various depth sensors. Our method first adopts a learning-based strategy where a neural network is trained to estimate a dense and complete depth map from polarization data and a sensor depth map from different sensors. To further improve the performance, we propose a Polarization Prompt Fusion Tuning (PPFT) strategy to effectively utilize RGB-based models pre-trained on large-scale datasets.
  arXiv  Detail & Related papers  (2024-04-05T17:55:33Z)
• DGNet: Dynamic Gradient-Guided Network for Water-Related Optics Image Enhancement [77.0360085530701]
  Underwater image enhancement (UIE) is a challenging task due to the complex degradation caused by underwater environments. Previous methods often idealize the degradation process, and neglect the impact of medium noise and object motion on the distribution of image features. Our approach utilizes predicted images to dynamically update pseudo-labels, adding a dynamic gradient to optimize the network's gradient space.
  arXiv  Detail & Related papers  (2023-12-12T06:07:21Z)
• NeISF: Neural Incident Stokes Field for Geometry and Material Estimation [50.588983686271284]
  Multi-view inverse rendering is the problem of estimating the scene parameters such as shapes, materials, or illuminations from a sequence of images captured under different viewpoints. We propose Neural Incident Stokes Fields (NeISF), a multi-view inverse framework that reduces ambiguities using polarization cues.
  arXiv  Detail & Related papers  (2023-11-22T06:28:30Z)
• Polarimetric Information for Multi-Modal 6D Pose Estimation of Photometrically Challenging Objects with Limited Data [51.95347650131366]
  6D pose estimation pipelines that rely on RGB-only or RGB-D data show limitations for photometrically challenging objects. A supervised learning-based method utilising complementary polarisation information is proposed to overcome such limitations.
  arXiv  Detail & Related papers  (2023-08-21T10:56:00Z)
• MS-PS: A Multi-Scale Network for Photometric Stereo With a New Comprehensive Training Dataset [0.0]
  Photometric stereo (PS) problem consists in reconstructing the 3D-surface of an object. We propose a multi-scale architecture for PS which, combined with a new dataset, yields state-of-the-art results.
  arXiv  Detail & Related papers  (2022-11-25T14:01:54Z)
• Polarized Color Image Denoising using Pocoformer [42.171036556122644]
  Polarized color photography provides both visual textures and object surficial information in one snapshot. The use of the directional polarizing filter array causes extremely lower photon count and SNR compared to conventional color imaging. We propose a learning-based approach to simultaneously restore clean signals and precise polarization information.
  arXiv  Detail & Related papers  (2022-07-01T05:52:14Z)
• Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN [92.15895515035795]
  We describe an approach for supervising deep networks that are based on CycleGAN. We introduce new losses for training CycleGAN that lead to more effective training, resulting in high-quality reconstructions. We demonstrate that the proposed method can be effectively applied to different restoration tasks like de-raining, de-hazing and de-snowing.
  arXiv  Detail & Related papers  (2022-04-23T01:30:47Z)
• Efficient and Differentiable Shadow Computation for Inverse Problems [64.70468076488419]
  Differentiable geometric computation has received increasing interest for image-based inverse problems. We propose an efficient yet efficient approach for differentiable visibility and soft shadow computation. As our formulation is differentiable, it can be used to solve inverse problems such as texture, illumination, rigid pose, and deformation recovery from images.
  arXiv  Detail & Related papers  (2021-04-01T09:29:05Z)
• Polarimetric image augmentation [0.7559720049837457]
  specular reflections impede autonomous navigation in urban environments. We propose to enhance deep learning models through a regularized augmentation procedure applied to polarimetric data. We observe an average of 18.1% improvement in IoU between non augmented and regularized training procedures on real world data.
  arXiv  Detail & Related papers  (2020-05-22T08:00:12Z)
• Deep Lighting Environment Map Estimation from Spherical Panoramas [0.0]
  We present a data-driven model that estimates an HDR lighting environment map from a single LDR monocular spherical panorama. We exploit the availability of surface geometry to employ image-based relighting as a data generator and supervision mechanism.
  arXiv  Detail & Related papers  (2020-05-16T14:23:05Z)

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.