paper-with-me

Papers

Geometric Point Attention Transformer for 3D Shape Reassembly

2024-11-26 · Jiahan Li, Chaoran Cheng, Jianzhu Ma, Ge Liu

Shape assembly, which aims to reassemble separate parts into a complete object, has gained significant interest in recent years. Existing methods primarily rely on networks to predict the poses of individual parts, but often fail to effectively capture the geometric interactions between the parts and their poses. In this paper, we present the Geometric Point Attention Transformer (GPAT), a network specifically designed to address the challenges of reasoning about geometric relationships. In the geometric point attention module, we integrate both global shape information and local pairwise geometric features, along with poses represented as rotation and translation vectors for each part. To enable iterative updates and dynamic reasoning, we introduce a geometric recycling scheme, where each prediction is fed into the next iteration for refinement. We evaluate our model on both the semantic and geometric assembly tasks, showing that it outperforms previous methods in absolute pose estimation, achieving accurate pose predictions and high alignment accuracy.

📄 PDF Abstract BibTeX arXiv:2411.17788

Code (0)

등록된 구현이 없습니다.

Tasks

Pose Estimation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
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…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Breaking Bad: A Dataset for Geometric Fracture and Reassembly

2022-10-20 · Silvia Sellán, Yun-Chun Chen, Ziyi Wu, Animesh Garg 외

We introduce Breaking Bad, a large-scale dataset of fractured objects. Our dataset consists of over one million fractured objects simulated from ten thousand base models. The fracture simulation is powered by a recent ph…

Object

SARe: Structure-Aware Generative 3D Fragment Reassembly

2026-03-23 · Hanze Jia, Chunshi Wang, Yuxiao Yang, Zhonghua Jiang 외 arxiv

3D fragment reassembly estimates the rigid pose of each fragment to recover a complete object from unordered point clouds or meshes. The task becomes increasingly challenging as the fragment count grows, since irregular …

Point Clouds

ReassembleNet: Learnable Keypoints and Diffusion for 2D Fresco Reconstruction

2025-05-27 · Adeela Islam, Stefano Fiorini, Stuart James, Pietro Morerio 외

The task of reassembly is a significant challenge across multiple domains, including archaeology, genomics, and molecular docking, requiring the precise placement and orientation of elements to reconstruct an original st…

Molecular DockingPose Estimation

E-M3RF: An Equivariant Multimodal 3D Re-assembly Framework

2025-11-26 · Adeela Islam, Stefano Fiorini, Manuel Lecha, Theodore Tsesmelis 외 arxiv

3D reassembly is a fundamental geometric problem, and in recent years it has increasingly been challenged by deep learning methods rather than classical optimization. While learning approaches have shown promising result…

Point Clouds

CSWin-UNet: Transformer UNet with Cross-Shaped Windows for Medical Image Segmentation

2024-07-25 · Xiao Liu, Peng Gao, Tao Yu, Fei Wang 외

Deep learning, especially convolutional neural networks (CNNs) and Transformer architectures, have become the focus of extensive research in medical image segmentation, achieving impressive results. However, CNNs come wi…

Computational EfficiencyDecoderImage SegmentationMedical Image Segmentation+2