English
Related papers

Related papers: SP$^2$T: Sparse Proxy Attention for Dual-stream Po…

200 papers

Semantic Segmentation is a crucial component in the perception systems of many applications, such as robotics and autonomous driving that rely on accurate environmental perception and understanding. In literature, several approaches are…

Computer Vision and Pattern Recognition · Computer Science 2021-03-17 Ran Cheng , Ryan Razani , Yuan Ren , Liu Bingbing

In this paper, we present Position-to-Structure Attention Transformers (PS-Former), a Transformer-based algorithm for 3D point cloud recognition. PS-Former deals with the challenge in 3D point cloud representation where points are not…

Computer Vision and Pattern Recognition · Computer Science 2022-10-06 Zheng Ding , James Hou , Zhuowen Tu

Diffusion Transformers (DiTs) deliver state-of-the-art generative performance but their quadratic training cost with sequence length makes large-scale pretraining prohibitively expensive. Token dropping can reduce training cost, yet na\"ive…

Computer Vision and Pattern Recognition · Computer Science 2026-01-12 Dogyun Park , Moayed Haji-Ali , Yanyu Li , Willi Menapace , Sergey Tulyakov , Hyunwoo J. Kim , Aliaksandr Siarohin , Anil Kag

Recent temporal LiDAR-based 3D object detectors achieve promising performance based on the two-stage proposal-based approach. They generate 3D box candidates from the first-stage dense detector, followed by different temporal aggregation…

Computer Vision and Pattern Recognition · Computer Science 2024-04-25 Kuan-Chih Huang , Weijie Lyu , Ming-Hsuan Yang , Yi-Hsuan Tsai

Diffusion Transformers (DiTs) deliver remarkable image and video generation quality but incur high computational cost, limiting scalability and on-device deployment. We introduce CoReDiT, a structured token pruning framework for DiTs across…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Zhuojin Li , Hsin-Pai Cheng , Hong Cai , Shizhong Han , Fatih Porikli

In recent years new application areas have emerged in which one aims to capture the geometry of objects by means of three-dimensional point clouds. Often the obtained data consist of a dense sampling of the object's surface, containing many…

Numerical Analysis · Mathematics 2019-10-01 Daniel Tenbrinck , Fjedor Gaede , Martin Burger

In autonomous driving, 3D object detection based on multi-modal data has become an indispensable approach when facing complex environments around the vehicle. During multi-modal detection, LiDAR and camera are simultaneously applied for…

Computer Vision and Pattern Recognition · Computer Science 2023-01-19 Rui Wan , Tianyun Zhao , Wei Zhao

Sparsifying the Transformer has garnered considerable interest, as training the Transformer is very computationally demanding. Prior efforts to sparsify the Transformer have either used a fixed pattern or data-driven approach to reduce the…

Machine Learning · Computer Science 2023-09-25 Bokyeong Yoon , Yoonsang Han , Gordon Euhyun Moon

Diffusion Transformers dominate video generation, but the quadratic complexity of attention computation introduces substantial latency. Attention sparsity reduces computational costs by focusing on critical tokens while ignoring…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Xuewen Liu , Zhikai Li , Jing Zhang , Mengjuan Chen , Qingyi Gu

Point cloud is a collection of 3D coordinates that are discrete geometric samples of an object's 2D surfaces. Using a low-cost 3D scanner to acquire data means that point clouds are often in lower resolution than desired for rendering on…

Signal Processing · Electrical Eng. & Systems 2019-08-20 Chinthaka Dinesh , Gene Cheung , Ivan V. Bajic

Transformer-based models have significantly advanced natural language processing and computer vision in recent years. However, due to the irregular and disordered structure of point cloud data, transformer-based models for 3D deep learning…

Computer Vision and Pattern Recognition · Computer Science 2023-04-07 Xincheng Yang , Mingze Jin , Weiji He , Qian Chen

The computational demands of self-attention mechanisms pose a critical challenge for transformer-based video generation, particularly in synthesizing ultra-long sequences. Current approaches, such as factorized attention and fixed sparse…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Qirui Li , Guangcong Zheng , Qi Zhao , Jie Li , Bin Dong , Yiwu Yao , Xi Li

Large-scale pre-trained diffusion models have been extensively adopted for real-world image Super-Resolution because of their powerful generative priors through textual guidance. However, when super-resolving high-resolution images with…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Qingji Dong , Hang Dong , Mingqin Chen , Rui Zhang , Yitong Wang

Recently Transformers have provided state-of-the-art performance in sparse matching, crucial to realize high-performance 3D vision applications. Yet, these Transformers lack efficiency due to the quadratic computational complexity of their…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Suwichaya Suwanwimolkul , Satoshi Komorita

3D surface reconstruction from point clouds is a key step in areas such as content creation, archaeology, digital cultural heritage, and engineering. Current approaches either try to optimize a non-data-driven surface representation to fit…

Computer Vision and Pattern Recognition · Computer Science 2024-02-09 Philipp Erler , Lizeth Fuentes , Pedro Hermosilla , Paul Guerrero , Renato Pajarola , Michael Wimmer

Scene flow enables an understanding of the motion characteristics of the environment in the 3D world. It gains particular significance in the long-range, where object-based perception methods might fail due to sparse observations far away.…

Computer Vision and Pattern Recognition · Computer Science 2025-01-30 Ajinkya Khoche , Qingwen Zhang , Laura Pereira Sanchez , Aron Asefaw , Sina Sharif Mansouri , Patric Jensfelt

As Large Language Models (LLMs) scale to million-token contexts, traditional Mechanistic Interpretability techniques for analyzing attention scale quadratically with context length, demanding terabytes of memory beyond 100,000 tokens. We…

Computation and Language · Computer Science 2026-02-03 J Rosser , José Luis Redondo García , Gustavo Penha , Konstantina Palla , Hugues Bouchard

We present a new two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD). The first stage is a bottom-up proposal generation network that uses raw point cloud as input to generate accurate proposals by…

Computer Vision and Pattern Recognition · Computer Science 2019-07-25 Zetong Yang , Yanan Sun , Shu Liu , Xiaoyong Shen , Jiaya Jia

Following the tremendous success of transformer in natural language processing and image understanding tasks, in this paper, we present a novel point cloud representation learning architecture, named Dual Transformer Network (DTNet), which…

Computer Vision and Pattern Recognition · Computer Science 2021-04-28 Xian-Feng Han , Yi-Fei Jin , Hui-Xian Cheng , Guo-Qiang Xiao

Deep neural networks are widely used for understanding 3D point clouds. At each point convolution layer, features are computed from local neighborhoods of 3D points and combined for subsequent processing in order to extract semantic…

Computer Vision and Pattern Recognition · Computer Science 2021-05-13 Jiayun Wang , Rudrasis Chakraborty , Stella X. Yu