English
Related papers

Related papers: Leveraging Equivariant Features for Absolute Pose …

200 papers

3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone, will look unrelated to each other after passing through to the…

Computer Vision and Pattern Recognition · Computer Science 2018-04-13 Daniel Worrall , Gabriel Brostow

Pose regression networks predict the camera pose of a query image relative to a known environment. Within this family of methods, absolute pose regression (APR) has recently shown promising accuracy in the range of a few centimeters in…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Shuai Chen , Tommaso Cavallari , Victor Adrian Prisacariu , Eric Brachmann

In this work, we focus on using convolution neural networks (CNN) to perform object recognition on the event data. In object recognition, it is important for a neural network to be robust to the variations of the data during testing. For…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Ziyun Wang

Estimating relative camera poses between images has been a central problem in computer vision. Methods that find correspondences and solve for the fundamental matrix offer high precision in most cases. Conversely, methods predicting pose…

Computer Vision and Pattern Recognition · Computer Science 2024-03-06 Chris Rockwell , Nilesh Kulkarni , Linyi Jin , Jeong Joon Park , Justin Johnson , David F. Fouhey

Equivariances provide useful inductive biases in neural network modeling, with the translation equivariance of convolutional neural networks being a canonical example. Equivariances can be embedded in architectures through weight-sharing…

Machine Learning · Computer Science 2022-11-15 Tycho F. A. van der Ouderaa , David W. Romero , Mark van der Wilk

Absolute Pose Regression (APR) methods use deep neural networks to directly regress camera poses from RGB images. However, the predominant APR architectures only rely on 2D operations during inference, resulting in limited accuracy of pose…

Computer Vision and Pattern Recognition · Computer Science 2024-03-04 Shuai Chen , Yash Bhalgat , Xinghui Li , Jiawang Bian , Kejie Li , Zirui Wang , Victor Adrian Prisacariu

Many robot manipulation tasks can be framed as geometric reasoning tasks, where an agent must be able to precisely manipulate an object into a position that satisfies the task from a set of initial conditions. Often, task success is defined…

Robotics · Computer Science 2024-04-23 Ben Eisner , Yi Yang , Todor Davchev , Mel Vecerik , Jonathan Scholz , David Held

Visual attributes are great means of describing images or scenes, in a way both humans and computers understand. In order to establish a correspondence between images and to be able to compare the strength of each property between images,…

Computer Vision and Pattern Recognition · Computer Science 2016-09-14 Yaser Souri , Erfan Noury , Ehsan Adeli

Detecting robust keypoints from an image is an integral part of many computer vision problems, and the characteristic orientation and scale of keypoints play an important role for keypoint description and matching. Existing learning-based…

Computer Vision and Pattern Recognition · Computer Science 2022-04-20 Jongmin Lee , Byungjin Kim , Minsu Cho

Many scientific problems require to process data in the form of geometric graphs. Unlike generic graph data, geometric graphs exhibit symmetries of translations, rotations, and/or reflections. Researchers have leveraged such inductive bias…

Machine Learning · Computer Science 2022-02-23 Jiaqi Han , Yu Rong , Tingyang Xu , Wenbing Huang

The convolutional layers of standard convolutional neural networks (CNNs) are equivariant to translation. However, the convolution and fully-connected layers are not equivariant or invariant to other affine geometric transformations.…

Computer Vision and Pattern Recognition · Computer Science 2022-09-23 Jaspreet Singh , Chandan Singh

In this paper, we address the problem of 6-DoF object pose estimation from a single RGB image. Indirect methods that typically predict intermediate 2D keypoints, followed by a Perspective-n-Point solver, have shown great performance. Direct…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Nassim Ali Ousalah , Peyman Rostami , Vincent Gaudillière , Emmanuel Koumandakis , Anis Kacem , Enjie Ghorbel , Djamila Aouada

Transfer learning for feature extraction can be used to exploit deep representations in contexts where there is very few training data, where there are limited computational resources, or when tuning the hyper-parameters needed for training…

Visual pose regression models estimate the camera pose from a query image with a single forward pass. Current models learn pose encoding from an image using deep convolutional networks which are trained per scene. The resulting encoding is…

Computer Vision and Pattern Recognition · Computer Science 2020-12-23 Yoli Shavit , Ron Ferens

Most deep pose estimation methods need to be trained for specific object instances or categories. In this work we propose a completely generic deep pose estimation approach, which does not require the network to have been trained on…

Computer Vision and Pattern Recognition · Computer Science 2019-08-06 Yang Xiao , Xuchong Qiu , Pierre-Alain Langlois , Mathieu Aubry , Renaud Marlet

Extracting discriminative local features that are invariant to imaging variations is an integral part of establishing correspondences between images. In this work, we introduce a self-supervised learning framework to extract discriminative…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Jongmin Lee , Byungjin Kim , Seungwook Kim , Minsu Cho

Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited data. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-02-10 Sayed Hashim , Muhammad Ali

In this paper, we introduce a novel RGB-D based relative pose estimation approach that is suitable for small-overlapping or non-overlapping scans and can output multiple relative poses. Our method performs scene completion and matches the…

Computer Vision and Pattern Recognition · Computer Science 2020-04-07 Zhenpei Yang , Siming Yan , Qixing Huang

Point cloud analysis is an area of increasing interest due to the development of 3D sensors that are able to rapidly measure the depth of scenes accurately. Unfortunately, applying deep learning techniques to perform point cloud analysis is…

Computer Vision and Pattern Recognition · Computer Science 2021-01-05 Junming Zhang , Ming-Yuan Yu , Ram Vasudevan , Matthew Johnson-Roberson

In this work, we address the problem of improvement of robustness of feature representations learned using convolutional neural networks (CNNs) to image deformation. We argue that higher moment statistics of feature distributions could be…

Computer Vision and Pattern Recognition · Computer Science 2017-07-26 Zhun Sun , Mete Ozay , Takayuki Okatani