Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation

• URL: http://arxiv.org/abs/2203.09836v1
• Date: Fri, 18 Mar 2022 10:20:21 GMT
• Title: Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation
• Authors: Yinlin Hu, Pascal Fua, Mathieu Salzmann
• Abstract summary: For some applications, such as those in space or deep under water, acquiring real images, even unannotated, is virtually impossible. We propose a method that can be trained solely on synthetic images, or optionally using a few additional real images. It performs on par with methods that require annotated real images for training when not using any, and outperforms them considerably when using as few as twenty real images.
• Score: 121.02948087956955
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most recent 6D object pose estimation methods, including unsupervised ones, require many real training images. Unfortunately, for some applications, such as those in space or deep under water, acquiring real images, even unannotated, is virtually impossible. In this paper, we propose a method that can be trained solely on synthetic images, or optionally using a few additional real ones. Given a rough pose estimate obtained from a first network, it uses a second network to predict a dense 2D correspondence field between the image rendered using the rough pose and the real image and infers the required pose correction. This approach is much less sensitive to the domain shift between synthetic and real images than state-of-the-art methods. It performs on par with methods that require annotated real images for training when not using any, and outperforms them considerably when using as few as twenty real images.

Related papers

• Adapting Skills to Novel Grasps: A Self-Supervised Approach [11.030216531050044]
  We study the problem of adapting manipulation trajectories involving grasped objects (e.g. tools) defined for a single grasp pose to novel grasp poses. A common approach to address this is to define a new trajectory for each possible grasp explicitly, but this is highly inefficient. We propose a method to adapt such trajectories directly while only requiring a period of self-supervised data collection.
  arXiv  Detail & Related papers  (2024-07-31T22:18:09Z)
• Pose-Free Neural Radiance Fields via Implicit Pose Regularization [117.648238941948]
  IR-NeRF is an innovative pose-free neural radiance field (NeRF) that introduces implicit pose regularization to refine pose estimator with unposed real images. With a collection of 2D images of a specific scene, IR-NeRF constructs a scene codebook that stores scene features and captures the scene-specific pose distribution implicitly as priors.
  arXiv  Detail & Related papers  (2023-08-29T06:14:06Z)
• Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation [14.469317161361202]
  We propose a 6D object pose estimation method that can be trained with pure RGB images without any auxiliary information. We evaluate our method on three challenging datasets and demonstrate that it outperforms state-of-the-art self-supervised methods significantly.
  arXiv  Detail & Related papers  (2023-08-19T13:52:18Z)
• TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation [55.94900327396771]
  We introduce neural texture learning for 6D object pose estimation from synthetic data. We learn to predict realistic texture of objects from real image collections. We learn pose estimation from pixel-perfect synthetic data.
  arXiv  Detail & Related papers  (2022-12-25T13:36:32Z)
• Unseen Object 6D Pose Estimation: A Benchmark and Baselines [62.8809734237213]
  We propose a new task that enables and facilitates algorithms to estimate the 6D pose estimation of novel objects during testing. We collect a dataset with both real and synthetic images and up to 48 unseen objects in the test set. By training an end-to-end 3D correspondences network, our method finds corresponding points between an unseen object and a partial view RGBD image accurately and efficiently.
  arXiv  Detail & Related papers  (2022-06-23T16:29:53Z)
• Object-Based Visual Camera Pose Estimation From Ellipsoidal Model and 3D-Aware Ellipse Prediction [2.016317500787292]
  We propose a method for initial camera pose estimation from just a single image. It exploits the ability of deep learning techniques to reliably detect objects regardless of viewing conditions. Experiments prove that the accuracy of the computed pose significantly increases thanks to our method.
  arXiv  Detail & Related papers  (2022-03-09T10:00:52Z)
• Two-shot Spatially-varying BRDF and Shape Estimation [89.29020624201708]
  We propose a novel deep learning architecture with a stage-wise estimation of shape and SVBRDF. We create a large-scale synthetic training dataset with domain-randomized geometry and realistic materials. Experiments on both synthetic and real-world datasets show that our network trained on a synthetic dataset can generalize well to real-world images.
  arXiv  Detail & Related papers  (2020-04-01T12:56:13Z)
• Introducing Pose Consistency and Warp-Alignment for Self-Supervised 6D Object Pose Estimation in Color Images [38.9238085806793]
  Most successful approaches to estimate the 6D pose of an object typically train a neural network by supervising the learning with annotated poses in real world images. A two-stage 6D object pose estimator framework that can be applied on top of existing neural-network-based approaches is proposed.
  arXiv  Detail & Related papers  (2020-03-27T11:53:38Z)
• Self-Supervised Linear Motion Deblurring [112.75317069916579]
  Deep convolutional neural networks are state-of-the-art for image deblurring. We present a differentiable reblur model for self-supervised motion deblurring. Our experiments demonstrate that self-supervised single image deblurring is really feasible.
  arXiv  Detail & Related papers  (2020-02-10T20:15:21Z)

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.