English
Related papers

Related papers: Flash3D: Super-scaling Point Transformers through …

200 papers

Recent advances in deep learning have improved 3D point cloud registration but increased graphics processing unit (GPU) memory usage, often requiring preliminary sampling that reduces accuracy. We propose an overlapping region sampling…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Tomoyasu Shimada , Kazuhiko Murasaki , Shogo Sato , Toshihiko Nishimura , Taiga Yoshida , Ryuichi Tanida

In this paper, we propose a new framework for online 3D scene perception. Conventional 3D scene perception methods are offline, i.e., take an already reconstructed 3D scene geometry as input, which is not applicable in robotic applications…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Xiuwei Xu , Chong Xia , Ziwei Wang , Linqing Zhao , Yueqi Duan , Jie Zhou , Jiwen Lu

Native 4K (2160$\times$3840) video generation remains a critical challenge due to the quadratic computational explosion of full-attention as spatiotemporal resolution increases, making it difficult for models to strike a balance between…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Jiangning Zhang , Junwei Zhu , Teng Hu , Yabiao Wang , Donghao Luo , Weijian Cao , Zhenye Gan , Xiaobin Hu , Zhucun Xue , Chengjie Wang

The transformer is the most critical algorithm innovation of the Nature Language Processing (NLP) field in recent years. Unlike the Recurrent Neural Network (RNN) models, Transformers can process on dimensions of sequence lengths in…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-02-23 Jiarui Fang , Yang Yu , Chengduo Zhao , Jie Zhou

Image matching is still challenging in such scenes with large viewpoints or illumination changes or with low textures. In this paper, we propose a Transformer-based pseudo 3D image matching method. It upgrades the 2D features extracted from…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Liming Han , Zhaoxiang Liu , Shiguo Lian

The task of detecting 3D objects in traffic scenes has a pivotal role in many real-world applications. However, the performance of 3D object detection is lower than that of 2D object detection due to the lack of powerful 3D feature…

Computer Vision and Pattern Recognition · Computer Science 2019-09-17 Xuesong Li , Jose Guivant , Ngaiming Kwok , Yongzhi Xu , Ruowei Li , Hongkun Wu

Self-attention modules have demonstrated remarkable capabilities in capturing long-range relationships and improving the performance of point cloud tasks. However, point cloud objects are typically characterized by complex, disordered, and…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Xian Wei , Muyu Wang , Shing-Ho Jonathan Lin , Zhengyu Li , Jian Yang , Arafat Al-Jawari , Xuan Tang

Voxel-based methods have achieved state-of-the-art performance for 3D object detection in autonomous driving. However, their significant computational and memory costs pose a challenge for their application to resource-constrained vehicles.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Tianchen Zhao , Xuefei Ning , Ke Hong , Zhongyuan Qiu , Pu Lu , Yali Zhao , Linfeng Zhang , Lipu Zhou , Guohao Dai , Huazhong Yang , Yu Wang

We present a novel approach for enhancing the resolution and geometric fidelity of 3D Gaussian Splatting (3DGS) beyond native training resolution. Current 3DGS methods are fundamentally limited by their input resolution, producing…

Graphics · Computer Science 2025-06-10 Shuja Khalid , Mohamed Ibrahim , Yang Liu

Existing convolutional learning methods for 3D point cloud data are divided into two paradigms: point-based methods that preserve geometric precision but often face performance challenges, and voxel-based methods that achieve high…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Lihan Li , Haofeng Zhong , Rui Bu , Mingchao Sun , Wenzheng Chen , Baoquan Chen , Yangyan Li

Self-attention mechanism has been a key factor in the recent progress of Vision Transformer (ViT), which enables adaptive feature extraction from global contexts. However, existing self-attention methods either adopt sparse global attention…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Xuran Pan , Tianzhu Ye , Zhuofan Xia , Shiji Song , Gao Huang

Monocular 3D lane detection is a fundamental task in autonomous driving. Although sparse-point methods lower computational load and maintain high accuracy in complex lane geometries, current methods fail to fully leverage the geometric…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Yifan Chang , Junjie Huang , Xiaofeng Wang , Yun Ye , Zhujin Liang , Yi Shan , Dalong Du , Xingang Wang

Domain-specific languages that execute image processing pipelineson GPUs, such as Halide and Forma, operate by 1) dividing the image into overlapped tiles, and 2) fusing loops to improve memory locality. However, current approaches have…

Programming Languages · Computer Science 2020-09-09 Abhinav Jangda , Arjun Guha

Deep learning-based feature matching has shown great superiority for point cloud registration in the absence of pose priors. Although coarse-to-fine matching approaches are prevalent, the coarse matching of existing methods is typically…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Renlang Huang , Yufan Tang , Jiming Chen , Liang Li

High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their per-pixel Gaussian prediction paradigm often suffers from…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Cheng Chi , Xianqi Wang , Hongcheng Luo , Mingfei Tu , Gangwei Xu , Zehan Zhang , Bing Wang , Guang Chen , Hangjun Ye , Sida Peng , Xin Yang , Haiyang Sun

We propose R3GS, a robust reconstruction and relocalization framework tailored for unconstrained datasets. Our method uses a hybrid representation during training. Each anchor combines a global feature from a convolutional neural network…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Xu yan , Zhaohui Wang , Rong Wei , Jingbo Yu , Dong Li , Xiangde Liu

Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong domain priors. This keeps the field isolated from the broader Transformer ecosystem, limiting…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Kadir Yilmaz , Adrian Kruse , Tristan Höfer , Daan de Geus , Bastian Leibe

Transformers have become central to natural language processing and large language models, but their deployment at scale faces three major challenges. First, the attention mechanism requires massive matrix multiplications and frequent…

Hardware Architecture · Computer Science 2026-01-22 Xiaoxuan Yang , Peilin Chen , Tergel Molom-Ochir , Yiran Chen

Transformer-based 3D reconstruction has emerged as a powerful paradigm for recovering geometry and appearance from multi-view observations, offering strong performance across challenging visual conditions. As these models scale to larger…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Haoyu Zhang , Zeyu Zhang , Zedong Zhou , Yang Zhao , Hao Tang

Parameter-efficient fine-tuning (PEFT) of pre-trained 3D point cloud Transformers has emerged as a promising technique for 3D point cloud analysis. While existing PEFT methods attempt to minimize the number of tunable parameters, they often…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Takahiko Furuya