English
Related papers

Related papers: ZipAR: Parallel Auto-regressive Image Generation t…

200 papers

We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…

Computer Vision and Pattern Recognition · Computer Science 2023-09-13 Yunhao Ge , Jiashu Xu , Brian Nlong Zhao , Neel Joshi , Laurent Itti , Vibhav Vineet

Composed Image Retrieval (CIR) aims to retrieve a target image based on a reference image and conditioning text, enabling controllable image searches. The mainstream Zero-Shot (ZS) CIR methods bypass the need for expensive training CIR…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Jaeseok Byun , Seokhyeon Jeong , Wonjae Kim , Sanghyuk Chun , Taesup Moon

VAR is a new generation paradigm that employs 'next-scale prediction' as opposed to 'next-token prediction'. This innovative transformation enables auto-regressive (AR) transformers to rapidly learn visual distributions and achieve robust…

Computer Vision and Pattern Recognition · Computer Science 2024-08-05 Qian Zhang , Xiangzi Dai , Ninghua Yang , Xiang An , Ziyong Feng , Xingyu Ren

Localization is a key challenge in many robotics applications. In this work we explore LIDAR-based global localization in both urban and natural environments and develop a method suitable for online application. Our approach leverages…

Robotics · Computer Science 2023-02-01 Georgi Tinchev , Adrian Penate-Sanchez , Maurice Fallon

Building accurate maps is a key building block to enable reliable localization, planning, and navigation of autonomous vehicles. We propose a novel approach for building accurate maps of dynamic environments utilizing a sequence of LiDAR…

Computer Vision and Pattern Recognition · Computer Science 2024-05-07 Xingguang Zhong , Yue Pan , Cyrill Stachniss , Jens Behley

Novel architectures have recently improved generative image synthesis leading to excellent visual quality in various tasks. Much of this success is due to the scalability of these architectures and hence caused by a dramatic increase in…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Andreas Blattmann , Robin Rombach , Kaan Oktay , Jonas Müller , Björn Ommer

Speculative decoding has proven to be an efficient solution to large language model (LLM) inference, where the small drafter predicts future tokens at a low cost, and the target model is leveraged to verify them in parallel. However, most…

Computation and Language · Computer Science 2024-10-10 Zilin Xiao , Hongming Zhang , Tao Ge , Siru Ouyang , Vicente Ordonez , Dong Yu

Integrating multiple generative foundation models, especially those trained on different modalities, into something greater than the sum of its parts poses significant challenges. Two key hurdles are the availability of aligned data…

Machine Learning · Computer Science 2024-06-03 Vicky Zayats , Peter Chen , Melissa Ferrari , Dirk Padfield

This paper proposes a novel Zero-Shot Action Recognition~(ZSAR) method based on contrastive learning. In ZSAR, we aim to classify examples from classes that were missing during training. Two well-known problems remain in ZSAR: the semantic…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Valter Estevam , Rayson Laroca , Helio Pedrini , David Menotti

Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior that captures rich…

Image and Video Processing · Electrical Eng. & Systems 2020-07-21 Xingang Pan , Xiaohang Zhan , Bo Dai , Dahua Lin , Chen Change Loy , Ping Luo

Our target is to learn visual correspondence from unlabeled videos. We develop LIIR, a locality-aware inter-and intra-video reconstruction framework that fills in three missing pieces, i.e., instance discrimination, location awareness, and…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Liulei Li , Tianfei Zhou , Wenguan Wang , Lu Yang , Jianwu Li , Yi Yang

Learning-based lossless image compression employs pixel-based or subimage-based auto-regression for probability estimation, which achieves desirable performances. However, the existing works only consider context dependencies in one…

Image and Video Processing · Electrical Eng. & Systems 2025-03-17 Tiantian Li , Qunbing Xia , Yue Li , Ruixiao Guo , Gaobo Yang

Zero-shot learning (ZSL) aims to recognize objects from novel unseen classes without any training data. Recently, structure-transfer based methods are proposed to implement ZSL by transferring structural knowledge from the semantic…

Computer Vision and Pattern Recognition · Computer Science 2017-11-21 Bo Zhao , Xinwei Sun , Yuan Yao , Yizhou Wang

Learning inter-image similarity is crucial for 3D medical images self-supervised pre-training, due to their sharing of numerous same semantic regions. However, the lack of the semantic prior in metrics and the semantic-independent variation…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Yuting He , Guanyu Yang , Rongjun Ge , Yang Chen , Jean-Louis Coatrieux , Boyu Wang , Shuo Li

Place recognition is an important capability for autonomously navigating vehicles operating in complex environments and under changing conditions. It is a key component for tasks such as loop closing in SLAM or global localization. In this…

Robotics · Computer Science 2023-04-21 Junyi Ma , Jun Zhang , Jintao Xu , Rui Ai , Weihao Gu , Xieyuanli Chen

Speculative decoding has been widely used to accelerate auto-regressive (AR) text generation. However, its effectiveness for visual AR models remains limited due to token selection ambiguity, where multiple tokens share similarly low…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Sihwan Park , Doohyuk Jang , Sungyub Kim , Souvik Kundu , Eunho Yang

Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with an encoder, and then recovers the masked inputs with a…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Maryam Haghighat , Peyman Moghadam , Shaheer Mohamed , Piotr Koniusz

Current state-of-the-art approaches for image captioning typically adopt an autoregressive manner, i.e., generating descriptions word by word, which suffers from slow decoding issue and becomes a bottleneck in real-time applications.…

Computer Vision and Pattern Recognition · Computer Science 2021-10-14 Xu Yan , Zhengcong Fei , Zekang Li , Shuhui Wang , Qingming Huang , Qi Tian

Synthetic aperture radar tomographic imaging reconstructs the three-dimensional reflectivity of a scene from a set of coherent acquisitions performed in an interferometric configuration. In forest areas, a large number of elements…

Image and Video Processing · Electrical Eng. & Systems 2024-02-09 Zoé Berenger , Loïc Denis , Florence Tupin , Laurent Ferro-Famil , Yue Huang

We propose SinIR, an efficient reconstruction-based framework trained on a single natural image for general image manipulation, including super-resolution, editing, harmonization, paint-to-image, photo-realistic style transfer, and artistic…

Computer Vision and Pattern Recognition · Computer Science 2021-06-15 Jihyeong Yoo , Qifeng Chen