English
Related papers

Related papers: SARA: Scene-Aware Reconstruction Accelerator

200 papers

With increasing diversity in Deep Neural Network(DNN) models in terms of layer shapes and sizes, the research community has been investigating flexible/reconfigurable accelerator substrates. This line of research has opened up two…

Hardware Architecture · Computer Science 2022-04-26 Ananda Samajdar , Michael Pellauer , Tushar Krishna

Recent video diffusion models (VDMs) synthesize visually convincing clips, yet still drop entities, mis-bind attributes, and weaken the interactions specified in the prompt. Representation-alignment objectives such as VideoREPA and MoAlign…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Jiesong Lian , Zixiang Zhou , Ruizhe Zhong , Yuan Zhou , Qinglin Lu , Rui Wang , Long Hu , Yixue Hao , Baoru Huang

Modern diffusion models encounter a fundamental trade-off between training efficiency and generation quality. While existing representation alignment methods, such as REPA, accelerate convergence through patch-wise alignment, they often…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Hesen Chen , Junyan Wang , Zhiyu Tan , Hao Li

3D fragment reassembly aims to recover the rigid poses of unordered fragment point clouds or meshes in a common object coordinate system to reconstruct the complete shape. The problem becomes particularly challenging as the number of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Hanze Jia , Chunshi Wang , Yuxiao Yang , Zhonghua Jiang , Yawei Luo , Shuainan Ye , Tan Tang

Automatic data augmentation (AutoDA) plays an important role in enhancing the generalization of neural networks. However, mainstream AutoDA methods often encounter two challenges: either the search process is excessively time-consuming,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Anqi Xiao , Weichen Yu , Hongyuan Yu

Retrieval-augmented Generation (RAG) extends large language models (LLMs) with external knowledge but faces key challenges: restricted effective context length and redundancy in retrieved documents. Pure compression-based approaches reduce…

Computation and Language · Computer Science 2025-07-09 Yiqiao Jin , Kartik Sharma , Vineeth Rakesh , Yingtong Dou , Menghai Pan , Mahashweta Das , Srijan Kumar

SARA integrates Eye Tracking and state-of-the-art large language models in a mixed reality framework to enhance the reading experience by providing personalized assistance in real-time. By tracking eye movements, SARA identifies the text…

Human-Computer Interaction · Computer Science 2024-04-11 Enkeleda Thaqi , Mohamed Mantawy , Enkelejda Kasneci

Conventional radar feature extraction faces limitations due to low spatial resolution, noise, multipath reflection, the presence of ghost targets, and motion blur. Such limitations can be exacerbated by nonlinear object motion, particularly…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Ryoma Yataka , Pu Perry Wang , Petros Boufounos , Ryuhei Takahashi

With the increasing number of parameters in large pre-trained models, LoRA as a parameter-efficient fine-tuning(PEFT) method is widely used for not adding inference overhead. The LoRA method assumes that weight changes during fine-tuning…

Machine Learning · Computer Science 2024-08-07 Jihao Gu , Shuai Chen , Zelin Wang , Yibo Zhang , Ping Gong

Reconstructing 3D shape and pose of static objects from a single image is an essential task for various industries, including robotics, augmented reality, and digital content creation. This can be done by directly predicting 3D shape in…

Computer Vision and Pattern Recognition · Computer Science 2023-10-18 Florian Langer , Ignas Budvytis , Roberto Cipolla

Simulated annealing tomography (SAT) is a simple iterative image reconstruction technique which can yield a superior reconstruction compared with filtered back-projection (FBP). However, the very high computational cost of iteratively…

Computational Physics · Physics 2014-11-18 Nghia T. Vo , Mark B. H. Breese , Herbert O. Moser

The surge of massive antenna arrays in wireless networks calls for the adoption of analog/hybrid array solutions, where multiple antenna elements are driven by a common radio front end to form a beam along a specific angle in order to…

Signal Processing · Electrical Eng. & Systems 2024-10-28 Silvio Mandelli , Marcus Henninger , Jinfeng Du

Recent progress in self-supervised representation learning has resulted in models that are capable of extracting image features that are not only effective at encoding image level, but also pixel-level, semantics. These features have been…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Octave Mariotti , Oisin Mac Aodha , Hakan Bilen

Homography estimation is the task of determining the transformation from an image pair. Our approach focuses on employing detector-free feature matching methods to address this issue. Previous work has underscored the importance of…

Information Retrieval · Computer Science 2024-10-15 Yuhan Liu , Qianxin Huang , Siqi Hui , Jingwen Fu , Sanping Zhou , Kangyi Wu , Pengna Li , Jinjun Wang

Rotating Synthetic Aperture Radar (ROSAR) can generate a 360$^\circ$ image of its surrounding environment using the collected data from a single moving track. Due to its non-linear track, the Back-Projection Algorithm (BPA) is commonly used…

Signal Processing · Electrical Eng. & Systems 2023-09-18 Wei Zhao , Cai Wen , Quan Yuan , Rong Zheng

Radars provide robust perception of vehicle surroundings by effectively functioning in poor light and adverse weather conditions. Synthetic aperture radar (SAR) algorithms are employed to address the limited angular resolution of radars by…

Signal Processing · Electrical Eng. & Systems 2026-03-10 S. Hamed Javadi , André Bourdoux , Adnan Albaba , Hichem Sahli

Object detection is essential to safe autonomous or assisted driving. Previous works usually utilize RGB images or LiDAR point clouds to identify and localize multiple objects in self-driving. However, cameras tend to fail in bad driving…

Computer Vision and Pattern Recognition · Computer Science 2021-07-06 Zangwei Zheng , Xiangyu Yue , Kurt Keutzer , Alberto Sangiovanni Vincentelli

Estimating 3D shapes and poses of static objects from a single image has important applications for robotics, augmented reality and digital content creation. Often this is done through direct mesh predictions which produces unrealistic,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Florian Langer , Gwangbin Bae , Ignas Budvytis , Roberto Cipolla

Great progress has been made in learning-based object detection methods in the last decade. Two-stage detectors often have higher detection accuracy than one-stage detectors, due to the use of region of interest (RoI) feature extractors…

Computer Vision and Pattern Recognition · Computer Science 2023-12-18 Guo-Ye Yang , George Kiyohiro Nakayama , Zi-Kai Xiao , Tai-Jiang Mu , Xiaolei Huang , Shi-Min Hu

Makeup transfer is a process of transferring the makeup style from a reference image to the source images, while preserving the source images' identities. This technique is highly desirable and finds many applications. However, existing…

Computer Vision and Pattern Recognition · Computer Science 2024-05-22 Xiaojing Zhong , Xinyi Huang , Zhonghua Wu , Guosheng Lin , Qingyao Wu
‹ Prev 1 2 3 10 Next ›