paper-with-me

홈 › Papers

3D Landmark Detection on Human Point Clouds: A Benchmark and A Dual Cascade Point Transformer Framework

2024-01-14 · Fan Zhang, Shuyi Mao, Qing Li, Xiaojiang Peng

3D landmark detection plays a pivotal role in various applications such as 3D registration, pose estimation, and virtual try-on. While considerable success has been achieved in 2D human landmark detection or pose estimation, there is a notable scarcity of reported works on landmark detection in unordered 3D point clouds. This paper introduces a novel challenge, namely 3D landmark detection on human point clouds, presenting two primary contributions. Firstly, we establish a comprehensive human point cloud dataset, named HPoint103, designed to support the 3D landmark detection community. This dataset comprises 103 human point clouds created with commercial software and actors, each manually annotated with 11 stable landmarks. Secondly, we propose a Dual Cascade Point Transformer (D-CPT) model for precise point-based landmark detection. D-CPT gradually refines the landmarks through cascade Transformer decoder layers across the entire point cloud stream, simultaneously enhancing landmark coordinates with a RefineNet over local regions. Comparative evaluations with popular point-based methods on HPoint103 and the public dataset DHP19 demonstrate the dramatic outperformance of our D-CPT. Additionally, the integration of our RefineNet into existing methods consistently improves performance.

📄 PDF Abstract BibTeX arXiv:2401.07251

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderPose EstimationVirtual Try-on

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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 $x$…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

LmPT: Conditional Point Transformer for Anatomical Landmark Detection on 3D Point Clouds

2026-02-02 · Matteo Bastico, Pierre Onghena, David Ryckelynck, Beatriz Marcotegui 외 arxiv

Accurate identification of anatomical landmarks is crucial for various medical applications. Traditional manual landmarking is time-consuming and prone to inter-observer variability, while rule-based methods are often ta…

Point Clouds

OccFace: Unified Occlusion-Aware Facial Landmark Detection with Per-Point Visibility

2026-02-11 · Xinhao Xiang, Zhengxin Li, Saurav Dhakad, Theo Bancroft 외 arxiv

Accurate facial landmark detection under occlusion remains challenging, especially for human-like faces with large appearance variation and rotation-driven self-occlusion. Existing detectors typically localize landmarks …

Facial Landmark Detection

Combining Deep Learning and Model-Based Methods for Robust Real-Time Semantic Landmark Detection

2019-09-02 · Benjamin Naujoks, Patrick Burger, Hans-Joachim Wuensche

Compared to abstract features, significant objects, so-called landmarks, are a more natural means for vehicle localization and navigation, especially in challenging unstructured environments. The major challenge is to re…

3D landmark detection for augmented reality based otologic procedures

2019-09-04 · Raabid Hussain, Alain Lalande, Kibrom Berihu Girum, Caroline Guigou 외

Ear consists of the smallest bones in the human body and does not contain significant amount of distinct landmark points that may be used to register a preoperative CT-scan with the surgical video in an augmented reality…

Interpretable Affordance Detection on 3D Point Clouds with Probabilistic Prototypes

2025-04-25 · Maximilian Xiling Li, Korbinian Rudolf, Nils Blank, Rudolf Lioutikov

Robotic agents need to understand how to interact with objects in their environment, both autonomously and during human-robot interactions. Affordance detection on 3D point clouds, which identifies object regions that al…

Affordance DetectionDecision Making