English
Related papers

Related papers: Hyperbolic Distillation: Geometry-Guided Cross-Mod…

200 papers

This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation. Directly employing previous distillation approaches yields inferior results due to the…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Yuenan Hou , Xinge Zhu , Yuexin Ma , Chen Change Loy , Yikang Li

Many recent works on 3D object detection have focused on designing neural network architectures that can consume point cloud data. While these approaches demonstrate encouraging performance, they are typically based on a single modality and…

Computer Vision and Pattern Recognition · Computer Science 2019-04-04 Vishwanath A. Sindagi , Yin Zhou , Oncel Tuzel

3D object detection is essential for understanding 3D scenes. Contemporary techniques often require extensive annotated training data, yet obtaining point-wise annotations for point clouds is time-consuming and laborious. Recent…

Computer Vision and Pattern Recognition · Computer Science 2024-08-02 Jiacheng Deng , Jiahao Lu , Tianzhu Zhang

We introduce DD3G, a formulation that Distills a multi-view Diffusion model (MV-DM) into a 3D Generator using gaussian splatting. DD3G compresses and integrates extensive visual and spatial geometric knowledge from the MV-DM by simulating…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Hao Qin , Luyuan Chen , Ming Kong , Mengxu Lu , Qiang Zhu

Recent advances in automotive four-dimensional (4D) Radar have enabled access to raw 4D Radar Tensor (4DRT), offering richer spatial and Doppler information than conventional point clouds. While most existing methods rely on heavily…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Seung-Hyun Song , Dong-Hee Paek , Minh-Quan Dao , Ezio Malis , Seung-Hyun Kong

Fusing LiDAR and camera information is essential for achieving accurate and reliable 3D object detection in autonomous driving systems. This is challenging due to the difficulty of combining multi-granularity geometric and semantic features…

Computer Vision and Pattern Recognition · Computer Science 2023-03-06 Yang Jiao , Zequn Jie , Shaoxiang Chen , Jingjing Chen , Lin Ma , Yu-Gang Jiang

The inherent noisy and sparse characteristics of radar data pose challenges in finding effective representations for 3D object detection. In this paper, we propose RadarDistill, a novel knowledge distillation (KD) method, which can improve…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Geonho Bang , Kwangjin Choi , Jisong Kim , Dongsuk Kum , Jun Won Choi

Though 3D object detection from point clouds has achieved rapid progress in recent years, the lack of flexible and high-performance proposal refinement remains a great hurdle for existing state-of-the-art two-stage detectors. Previous works…

Computer Vision and Pattern Recognition · Computer Science 2021-09-16 Hualian Sheng , Sijia Cai , Yuan Liu , Bing Deng , Jianqiang Huang , Xian-Sheng Hua , Min-Jian Zhao

Object detection has achieved remarkable accuracy through deep learning, yet these improvements often come with increased computational cost, limiting deployment on resource-constrained devices. Knowledge Distillation (KD) provides an…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Mahdi Golizadeh , Nassibeh Golizadeh , Mohammad Ali Keyvanrad , Hossein Shirazi

Recently, Transformer has achieved great success in computer vision. However, it is constrained because the spatial and temporal complexity grows quadratically with the number of large points in 3D object detection applications. Previous…

Computer Vision and Pattern Recognition · Computer Science 2022-11-11 Jigang Tong , Fanhang Yang , Sen Yang , Enzeng Dong , Shengzhi Du , Xing Wang , Xianlin Yi

Infrared and visible dual-modality tasks such as semantic segmentation and object detection can achieve robust performance even in extreme scenes by fusing complementary information. Most current methods design task-specific frameworks,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-17 Fangcen Liu , Chenqiang Gao , Fang Chen , Pengcheng Li , Junjie Guo , Deyu Meng

To achieve reliable and precise scene understanding, autonomous vehicles typically incorporate multiple sensing modalities to capitalize on their complementary attributes. However, existing cross-modal 3D detectors do not fully utilize the…

Computer Vision and Pattern Recognition · Computer Science 2023-10-20 Yifan Zhang , Qijian Zhang , Junhui Hou , Yixuan Yuan , Guoliang Xing

Place recognition is an important task for robots and autonomous cars to localize themselves and close loops in pre-built maps. While single-modal sensor-based methods have shown satisfactory performance, cross-modal place recognition that…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Weidong Xie , Lun Luo , Nanfei Ye , Yi Ren , Shaoyi Du , Minhang Wang , Jintao Xu , Rui Ai , Weihao Gu , Xieyuanli Chen

Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic sets while preserving training efficacy. However, existing studies mainly focus on image classification, leaving dense prediction tasks such as semantic…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Wenjie Zheng , Haoji Hu , Jiali Lu , Xingze Zou , Jing Wang

Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…

Computer Vision and Pattern Recognition · Computer Science 2022-09-19 Tianfang Sun , Zhizhong Zhang , Xin Tan , Yanyun Qu , Yuan Xie , Lizhuang Ma

General object composition (GOC) aims to seamlessly integrate a target object into a background scene with desired geometric properties, while simultaneously preserving its fine-grained appearance details. Recent approaches derive semantic…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Jianman Lin , Haojie Li , Chunmei Qing , Zhijing Yang , Liang Lin , Tianshui Chen

Good 3D object detection performance from LiDAR-Camera sensors demands seamless feature alignment and fusion strategies. We propose the 3DifFusionDet framework in this paper, which structures 3D object detection as a denoising diffusion…

Computer Vision and Pattern Recognition · Computer Science 2023-11-08 Xinhao Xiang , Simon Dräger , Jiawei Zhang

Accurate detection of obstacles in 3D is an essential task for autonomous driving and intelligent transportation. In this work, we propose a general multimodal fusion framework FusionPainting to fuse the 2D RGB image and 3D point clouds at…

Computer Vision and Pattern Recognition · Computer Science 2021-08-11 Shaoqing Xu , Dingfu Zhou , Jin Fang , Junbo Yin , Zhou Bin , Liangjun Zhang

Hyperspectral point clouds (HPCs) can simultaneously characterize 3D spatial and spectral information of ground objects, offering excellent 3D perception and target recognition capabilities. Current approaches for generating HPCs often…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Yanze Jiang , Yanfeng Gu , Xian Li

In this work, we propose a novel two-stage framework for the efficient 3D point cloud object detection. Instead of transforming point clouds into 2D bird eye view projections, we parse the raw point cloud data directly in the 3D space yet…

Computer Vision and Pattern Recognition · Computer Science 2021-07-28 Zhaoyu Su , Pin Siang Tan , Yu-Hsing Wang