paper-with-me

Papers

CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer

2024-06-12 · Hualian Sheng, Sijia Cai, Na Zhao, Bing Deng, Qiao Liang, Min-Jian Zhao, Jieping Ye

The field of 3D object detection from point clouds is rapidly advancing in computer vision, aiming to accurately and efficiently detect and localize objects in three-dimensional space. Current 3D detectors commonly fall short in terms of flexibility and scalability, with ample room for advancements in performance. In this paper, our objective is to address these limitations by introducing two frameworks for 3D object detection with minimal hand-crafted design. Firstly, we propose CT3D, which sequentially performs raw-point-based embedding, a standard Transformer encoder, and a channel-wise decoder for point features within each proposal. Secondly, we present an enhanced network called CT3D++, which incorporates geometric and semantic fusion-based embedding to extract more valuable and comprehensive proposal-aware information. Additionally, CT3D ++ utilizes a point-to-key bidirectional encoder for more efficient feature encoding with reduced computational cost. By replacing the corresponding components of CT3D with these novel modules, CT3D++ achieves state-of-the-art performance on both the KITTI dataset and the large-scale Way\-mo Open Dataset. The source code for our frameworks will be made accessible at https://github.com/hlsheng1/CT3D-plusplus.

📄 PDF Abstract BibTeX arXiv:2406.08152

Code (1)

hlsheng1/ct3d-plusplus 공식 구현 pytorch

Tasks

3D Object DetectionDecoderobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
CT3D 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Improving 3D Object Detection with Channel-wise Transformer

2021-08-23 · ICCV 2021 10 · Hualian Sheng, Sijia Cai, YuAn Liu, Bing Deng 외

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 detec…

3D Object DetectionObjectobject-detectionObject Detection+1

PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection

2022-08-29 · Peng Wu, Lipeng Gu, Xuefeng Yan, Haoran Xie 외

Large imbalance often exists between the foreground points (i.e., objects) and the background points in outdoor LiDAR point clouds. It hinders cutting-edge detectors from focusing on informative areas to produce accurate…

3D Object DetectionNovel Object DetectionObjectobject-detection+2

UR2KiD: Unifying Retrieval, Keypoint Detection, and Keypoint Description without Local Correspondence Supervision

2020-01-20 · Tsun-Yi Yang, Duy-Kien Nguyen, Huub Heijnen, Vassileios Balntas

In this paper, we explore how three related tasks, namely keypoint detection, description, and image retrieval can be jointly tackled using a single unified framework, which is trained without the need of training data w…

Image RetrievalKeypoint DetectionRetrieval

Siamese Attentional Keypoint Network for High Performance Visual Tracking

2019-04-23 · Peng Gao, Ruyue Yuan, Fei Wang, Liyi Xiao 외

In this paper, we investigate the impacts of three main aspects of visual tracking, i.e., the backbone network, the attentional mechanism, and the detection component, and propose a Siamese Attentional Keypoint Network, …

Visual TrackingVocal Bursts Intensity Prediction

DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection

2025-03-10 · Johan Edstedt, Georg Bökman, Mårten Wadenbäck, Michael Felsberg

Keypoints are what enable Structure-from-Motion (SfM) systems to scale to thousands of images. However, designing a keypoint detection objective is a non-trivial task, as SfM is non-differentiable. Typically, an auxiliar…

Keypoint Detectionreinforcement-learningReinforcement Learning