English
Related papers

Related papers: Shape-Pose Disentanglement using SE(3)-equivariant…

200 papers

Neural networks that incorporate geometric relationships respecting SE(3) group transformations (e.g. rotations and translations) are increasingly important in molecular applications, such as molecular property prediction, protein structure…

Machine Learning · Computer Science 2025-10-21 Jose Siguenza , Bharath Ramsundar

We propose DenseMarks - a new learned representation for human heads, enabling high-quality dense correspondences of human head images. For a 2D image of a human head, a Vision Transformer network predicts a 3D embedding for each pixel,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Dmitrii Pozdeev , Alexey Artemov , Ananta R. Bhattarai , Artem Sevastopolsky

Spherical equivariant graph neural networks (EGNNs) provide a principled framework for learning on three-dimensional molecular and biomolecular systems, where predictions must respect the rotational symmetries inherent in physics. These…

Machine Learning · Computer Science 2025-12-17 Sophia Tang

We propose a new encoder-decoder approach to learn distributed sentence representations that are applicable to multiple purposes. The model is learned by using a convolutional neural network as an encoder to map an input sentence into a…

Computation and Language · Computer Science 2017-07-28 Zhe Gan , Yunchen Pu , Ricardo Henao , Chunyuan Li , Xiaodong He , Lawrence Carin

While end-to-end approaches have achieved state-of-the-art performance in many perception tasks, they are not yet able to compete with 3D geometry-based methods in pose estimation. Moreover, absolute pose regression has been shown to be…

Computer Vision and Pattern Recognition · Computer Science 2022-04-06 Mohamed Adel Musallam , Vincent Gaudilliere , Miguel Ortiz del Castillo , Kassem Al Ismaeil , Djamila Aouada

Inspired by recent advances in multimodal learning and machine translation, we introduce an encoder-decoder pipeline that learns (a): a multimodal joint embedding space with images and text and (b): a novel language model for decoding…

Machine Learning · Computer Science 2014-11-11 Ryan Kiros , Ruslan Salakhutdinov , Richard S. Zemel

Positional encodings are a common component of neural scene reconstruction methods, and provide a way to bias the learning of neural fields towards coarser or finer representations. Current neural surface reconstruction methods use a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Thomas Walker , Octave Mariotti , Amir Vaxman , Hakan Bilen

Predicting the pose of objects from a single image is an important but difficult computer vision problem. Methods that predict a single point estimate do not predict the pose of objects with symmetries well and cannot represent uncertainty.…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 David M. Klee , Ondrej Biza , Robert Platt , Robin Walters

We present a novel learning approach to recover the 6D poses and sizes of unseen object instances from an RGB-D image. To handle the intra-class shape variation, we propose a deep network to reconstruct the 3D object model by explicitly…

Computer Vision and Pattern Recognition · Computer Science 2020-07-17 Meng Tian , Marcelo H Ang , Gim Hee Lee

Features that are equivariant to a larger group of symmetries have been shown to be more discriminative and powerful in recent studies. However, higher-order equivariant features often come with an exponentially-growing computational cost.…

Computer Vision and Pattern Recognition · Computer Science 2021-04-05 Haiwei Chen , Shichen Liu , Weikai Chen , Hao Li

Neural implicit functions have achieved impressive results for reconstructing 3D shapes from single images. However, the image features for describing 3D point samplings of implicit functions are less effective when significant variations…

Computer Vision and Pattern Recognition · Computer Science 2022-02-01 Yixin Zhuang , Yunzhe Liu , Yujie Wang , Baoquan Chen

Deep feature spaces have the capacity to encode complex transformations of their input data. However, understanding the relative feature-space relationship between two transformed encoded images is difficult. For instance, what is the…

Computer Vision and Pattern Recognition · Computer Science 2017-10-23 Daniel E. Worrall , Stephan J. Garbin , Daniyar Turmukhambetov , Gabriel J. Brostow

A crucial problem in learning disentangled image representations is controlling the degree of disentanglement during image editing, while preserving the identity of objects. In this work, we propose a simple yet effective model with the…

Machine Learning · Computer Science 2019-12-30 Zengjie Song , Oluwasanmi Koyejo , Jiangshe Zhang

Accurately estimating the pose of an object is a crucial task in computer vision and robotics. There are two main deep learning approaches for this: geometric representation regression and iterative refinement. However, these methods have…

Computer Vision and Pattern Recognition · Computer Science 2024-01-30 Jaewoo Park , Jaeguk Kim , Nam Ik Cho

Learning model-free object pose estimation for unseen instances remains a fundamental challenge in 3D vision. Existing methods typically fall into two disjoint paradigms: category-level approaches predict absolute poses in a canonical space…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Weihang Li , Lorenzo Garattoni , Fabien Despinoy , Nassir Navab , Benjamin Busam

Rotation equivariance is a desirable property in many practical applications such as motion forecasting and 3D perception, where it can offer benefits like sample efficiency, better generalization, and robustness to input perturbations.…

Computer Vision and Pattern Recognition · Computer Science 2023-01-26 Serge Assaad , Carlton Downey , Rami Al-Rfou , Nigamaa Nayakanti , Ben Sapp

Graph neural networks that model 3D data, such as point clouds or atoms, are typically desired to be $SO(3)$ equivariant, i.e., equivariant to 3D rotations. Unfortunately equivariant convolutions, which are a fundamental operation for…

Machine Learning · Computer Science 2023-06-16 Saro Passaro , C. Lawrence Zitnick

PointNet has recently emerged as a popular representation for unstructured point cloud data, allowing application of deep learning to tasks such as object detection, segmentation and shape completion. However, recent works in literature…

Computer Vision and Pattern Recognition · Computer Science 2019-12-13 Vinit Sarode , Xueqian Li , Hunter Goforth , Yasuhiro Aoki , Animesh Dhagat , Rangaprasad Arun Srivatsan , Simon Lucey , Howie Choset

We propose a deep autoencoder with graph topology inference and filtering to achieve compact representations of unorganized 3D point clouds in an unsupervised manner. Many previous works discretize 3D points to voxels and then use…

Computer Vision and Pattern Recognition · Computer Science 2020-02-19 Siheng Chen , Chaojing Duan , Yaoqing Yang , Duanshun Li , Chen Feng , Dong Tian

Quantum Computing offers a potentially powerful new method for performing Machine Learning. However, several Quantum Machine Learning techniques have been shown to exhibit poor generalisation as the number of qubits increases. We address…

Quantum Physics · Physics 2024-05-21 Jamie Heredge , Charles Hill , Lloyd Hollenberg , Martin Sevior