English
Related papers

Related papers: Anisotropic Fourier Features for Positional Encodi…

200 papers

Positional embeddings (PE) play a crucial role in Vision Transformers (ViTs) by providing spatial information otherwise lost due to the permutation invariant nature of self attention. While absolute positional embeddings (APE) have shown…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Md Abtahi Majeed Chowdhury , Md Rifat Ur Rahman , Akil Ahmad Taki

Inpainting-based codecs store sparse selected pixel data and decode by reconstructing the discarded image parts by inpainting. Successful codecs (coders and decoders) traditionally use inpainting operators that solve partial differential…

Image and Video Processing · Electrical Eng. & Systems 2024-06-21 Rahul Mohideen Kaja Mohideen , Tobias Alt , Pascal Peter , Joachim Weickert

Implicit neural representation (INR) is a popular approach for arbitrary-scale image super-resolution (SR), as a key component of INR, position encoding improves its representation ability. Motivated by position encoding, we propose…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Gaochao Song , Luo Zhang , Ran Su , Jianfeng Shi , Ying He , Qian Sun

Many positional encodings (PEs) are designed to exhibit long-term decay, based on an entrenched and long-standing inductive opinion: tokens farther away from the current position carry less relevant information. We argue that long-term…

Computation and Language · Computer Science 2024-12-06 Yuhan Chen , Ang Lv , Jian Luan , Bin Wang , Wei Liu

We propose a conditional positional encoding (CPE) scheme for vision Transformers. Unlike previous fixed or learnable positional encodings, which are pre-defined and independent of input tokens, CPE is dynamically generated and conditioned…

Computer Vision and Pattern Recognition · Computer Science 2023-02-14 Xiangxiang Chu , Zhi Tian , Bo Zhang , Xinlong Wang , Chunhua Shen

Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this study is to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Philipp Wesp , Robbie Holland , Vasiliki Sideri-Lampretsa , Sergios Gatidis

Rotary Position Embedding (RoPE) is the de facto positional encoding in large language models due to its ability to encode relative positions and support length extrapolation. When adapted to vision transformers, the standard axial…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Haoyu Liu , Sucheng Ren , Tingyu Zhu , Peng Wang , Cihang Xie , Alan Yuille , Zeyu Zheng , Feng Wang

Human pose estimation (HPE) usually requires large-scale training data to reach high performance. However, it is rather time-consuming to collect high-quality and fine-grained annotations for human body. To alleviate this issue, we revisit…

Computer Vision and Pattern Recognition · Computer Science 2022-05-26 Xixia Xu , Yingguo Gao , Ke Yan , Xue Lin , Qi Zou

Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks, yet often suffer from inefficiencies due to redundant visual tokens. Existing token merging methods reduce sequence length but frequently…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Mouxiao Huang , Borui Jiang , Dehua Zheng , Hailin Hu , Kai Han , Xinghao Chen

Transformers have recently been shown to generate high quality images from text input. However, the existing method of pose conditioning using skeleton image tokens is computationally inefficient and generate low quality images. Therefore…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Soon Yau Cheong , Armin Mustafa , Andrew Gilbert

Transformers are increasingly prevalent for multi-view computer vision tasks, where geometric relationships between viewpoints are critical for 3D perception. To leverage these relationships, multi-view transformers must use camera geometry…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Ruilong Li , Brent Yi , Junchen Liu , Hang Gao , Yi Ma , Angjoo Kanazawa

Neural implicit fields, such as the neural signed distance field (SDF) of a shape, have emerged as a powerful representation for many applications, e.g., encoding a 3D shape and performing collision detection. Typically, implicit fields are…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Guying Lin , Lei Yang , Yuan Liu , Congyi Zhang , Junhui Hou , Xiaogang Jin , Taku Komura , John Keyser , Wenping Wang

Vision transformers have demonstrated significant advantages in computer vision tasks due to their ability to capture long-range dependencies and contextual relationships through self-attention. However, existing position encoding…

Computer Vision and Pattern Recognition · Computer Science 2025-05-15 Xi Chen , Shiyang Zhou , Muqi Huang , Jiaxu Feng , Yun Xiong , Kun Zhou , Biao Yang , Yuhui Zhang , Huishuai Bao , Sijia Peng , Chuan Li , Feng Shi

Since self-attention layers in Transformers are permutation invariant by design, positional encodings must be explicitly incorporated to enable spatial understanding. However, fixed-size lookup tables used in traditional learnable position…

Machine Learning · Computer Science 2025-06-18 Huayang Li , Yahui Liu , Hongyu Sun , Deng Cai , Leyang Cui , Wei Bi , Peilin Zhao , Taro Watanabe

Fourier ptychography (FP) is an enabling imaging technique that produces high-resolution complex-valued images with extended field coverages. However, when FP images a phase object with any specific spatial frequency, the captured images…

Neural networks that map between low dimensional spaces are ubiquitous in computer graphics and scientific computing; however, in their naive implementation, they are unable to learn high frequency information. We present a comprehensive…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 Samuel Audia , Soheil Feizi , Matthias Zwicker , Dinesh Manocha

Transformer architectures rely on position encodings to model the spatial structure of input data. Rotary Position Encoding (RoPE) is a widely used method in language models that encodes relative positions through fixed, block-diagonal,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Sophie Ostmeier , Brian Axelrod , Maya Varma , Michael E. Moseley , Akshay Chaudhari , Curtis Langlotz

Purpose: To achieve automatic hyperparameter estimation for the joint recovery of quantitative MR images, we propose a Bayesian formulation of the reconstruction problem that incorporates the signal model. Additionally, we investigate the…

Image and Video Processing · Electrical Eng. & Systems 2023-09-12 Shuai Huang , James J. Lah , Jason W. Allen , Deqiang Qiu

Monocular 3D human pose estimation (HPE) methods estimate the 3D positions of joints from individual images. Existing 3D HPE approaches often use the cropped image alone as input for their models. However, the relative depths of joints…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Xiaoyang Hao , Han Li

Deconvolution of the telescope Point Spread Function (PSF) is necessary for even moderate dynamic range imaging with interferometric telescopes. The process of deconvolution can be treated as a search for a model image such that the…

Astrophysics · Physics 2009-11-10 S. Bhatnagar , T. J. Cornwell