English
Related papers

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

200 papers

Most existing 3D instance segmentation methods are derived from 3D semantic segmentation models. However, these indirect approaches suffer from certain limitations. They fail to fully leverage global and local semantic information for…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Lei Pan , Wuyang Luan , Yuan Zheng , Qiang Fu , Junhui Li

Point cloud completion aims to reconstruct the complete 3D shape from incomplete point clouds, and it is crucial for tasks such as 3D object detection and segmentation. Despite the continuous advances in point cloud analysis techniques,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Yi Zhong , Weize Quan , Dong-ming Yan , Jie Jiang , Yingmei Wei

An efficient attention implementation is essential for large models due to its quadratic time complexity. Fortunately, attention commonly exhibits sparsity, i.e., many values in the attention map are near zero, allowing for the omission of…

Machine Learning · Computer Science 2025-11-20 Jintao Zhang , Chendong Xiang , Haofeng Huang , Jia Wei , Haocheng Xi , Jun Zhu , Jianfei Chen

This paper presents PipeFusion, an innovative parallel methodology to tackle the high latency issues associated with generating high-resolution images using diffusion transformers (DiTs) models. PipeFusion partitions images into patches and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Jiarui Fang , Jinzhe Pan , Aoyu Li , Xibo Sun , Jiannan Wang

Point-based representations have consistently played a vital role in geometric data structures. Most point cloud learning and processing methods typically leverage the unordered and unconstrained nature to represent the underlying geometry…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Jionghao Wang , Cheng Lin , Yuan Liu , Rui Xu , Zhiyang Dou , Xiao-Xiao Long , Hao-Xiang Guo , Taku Komura , Wenping Wang , Xin Li

Point clouds collected by real-world sensors are always unaligned and sparse, which makes it hard to reconstruct the complete shape of object from a single frame of data. In this work, we manage to provide complete point clouds from sparse…

Computer Vision and Pattern Recognition · Computer Science 2022-02-08 Jieqi Shi , Lingyun Xu , Peiliang Li , Xiaozhi Chen , Shaojie Shen

Optical flow estimation aims to find the 2D motion field by identifying corresponding pixels between two images. Despite the tremendous progress of deep learning-based optical flow methods, it remains a challenge to accurately estimate…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Xiuchao Sui , Shaohua Li , Xue Geng , Yan Wu , Xinxing Xu , Yong Liu , Rick Goh , Hongyuan Zhu

Radar-based perception has gained increasing attention in autonomous driving, yet the inherent sparsity of radars poses challenges. Radar raw data often contains excessive noise, whereas radar point clouds retain only limited information.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-16 Jialong Wu , Mirko Meuter , Markus Schoeler , Matthias Rottmann

The evolution of Vision Transformers has led to their widespread adaptation to different domains. Despite large-scale success, there remain significant challenges including their reliance on extensive computational and memory resources for…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Suyash Gaurav , Muhammad Farhan Humayun , Jukka Heikkonen , Jatin Chaudhary

3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects. In this paper, we analyze major components of existing sparse 3D CNNs and find that…

Computer Vision and Pattern Recognition · Computer Science 2022-09-29 Jianhui Liu , Yukang Chen , Xiaoqing Ye , Zhuotao Tian , Xiao Tan , Xiaojuan Qi

Diffusion Transformers are fundamental for video and image generation, but their efficiency is bottlenecked by the quadratic complexity of attention. While block sparse attention accelerates computation by attending only critical key-value…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Haopeng Li , Shitong Shao , Wenliang Zhong , Zikai Zhou , Lichen Bai , Hui Xiong , Zeke Xie

Point-cloud-based 3D perception has attracted great attention in various applications including robotics, autonomous driving and AR/VR. In particular, the 3D sparse convolution (SpConv) network has emerged as one of the most popular…

Hardware Architecture · Computer Science 2023-08-21 Dongxu Lyu , Zhenyu Li , Yuzhou Chen , Jinming Zhang , Ningyi Xu , Guanghui He

The structured light (SL)-based three-dimensional (3D) measurement techniques with deep learning have been widely studied to improve measurement efficiency, among which fringe projection profilometry (FPP) and speckle projection…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Mingyang Lei , Jingfan Fan , Long Shao , Hong Song , Deqiang Xiao , Danni Ai , Tianyu Fu , Ying Gu , Jian Yang

Most existing methods realize 3D instance segmentation by extending those models used for 3D object detection or 3D semantic segmentation. However, these non-straightforward methods suffer from two drawbacks: 1) Imprecise bounding boxes or…

Computer Vision and Pattern Recognition · Computer Science 2022-11-30 Jiahao Sun , Chunmei Qing , Junpeng Tan , Xiangmin Xu

Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to long token sequences. Recent Top-K sparse attention approaches reduce the computation of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Yifan Zhou , Zeqi Xiao , Tianyi Wei , Shuai Yang , Xingang Pan

Transformers' quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used by entmax transformers, consists of having built-in exact…

Computation and Language · Computer Science 2022-04-22 Marcos Treviso , António Góis , Patrick Fernandes , Erick Fonseca , André F. T. Martins

Recent Transformer-based 3D object detectors learn point cloud features either from point- or voxel-based representations. However, the former requires time-consuming sampling while the latter introduces quantization errors. In this paper,…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Honghui Yang , Wenxiao Wang , Minghao Chen , Binbin Lin , Tong He , Hua Chen , Xiaofei He , Wanli Ouyang

Most recent works on optical flow use convex upsampling as the last step to obtain high-resolution flow. In this work, we show and discuss several issues and limitations of this currently widely adopted convex upsampling approach. We…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Alexander Gielisse , Nergis Tömen , Jan van Gemert

Scene flow depicts the dynamics of a 3D scene, which is critical for various applications such as autonomous driving, robot navigation, AR/VR, etc. Conventionally, scene flow is estimated from dense/regular RGB video frames. With the…

Computer Vision and Pattern Recognition · Computer Science 2021-12-07 Haiyan Wang , Jiahao Pang , Muhammad A. Lodhi , Yingli Tian , Dong Tian

Generating high-resolution 3D shapes using volumetric representations such as Signed Distance Functions (SDFs) presents substantial computational and memory challenges. We introduce Direct3D-S2, a scalable 3D generation framework based on…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Shuang Wu , Youtian Lin , Feihu Zhang , Yifei Zeng , Yikang Yang , Yajie Bao , Jiachen Qian , Siyu Zhu , Xun Cao , Philip Torr , Yao Yao