paper-with-me

홈 › Papers

Jigsaw: Learning to Assemble Multiple Fractured Objects

2023-05-29 · NeurIPS 2023 11 · Jiaxin Lu, Yifan Sun, QiXing Huang

Automated assembly of 3D fractures is essential in orthopedics, archaeology, and our daily life. This paper presents Jigsaw, a novel framework for assembling physically broken 3D objects from multiple pieces. Our approach leverages hierarchical features of global and local geometry to match and align the fracture surfaces. Our framework consists of four components: (1) front-end point feature extractor with attention layers, (2) surface segmentation to separate fracture and original parts, (3) multi-parts matching to find correspondences among fracture surface points, and (4) robust global alignment to recover the global poses of the pieces. We show how to jointly learn segmentation and matching and seamlessly integrate feature matching and rigidity constraints. We evaluate Jigsaw on the Breaking Bad dataset and achieve superior performance compared to state-of-the-art methods. Our method also generalizes well to diverse fracture modes, objects, and unseen instances. To the best of our knowledge, this is the first learning-based method designed specifically for 3D fracture assembly over multiple pieces. Our code is available at https://jiaxin-lu.github.io/Jigsaw/.

📄 PDF Abstract BibTeX arXiv:2305.17975

Code (1)

jiaxin-lu/jigsaw pytorch

Methods 이 논문이 사용한 방법론

Jigsaw Jigsaw is a self-supervision approach that relies on jigsaw-like puzzles as the pretext task in order to learn image representations.
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repair

2022-11-22 · Nikolas Lamb, Sean Banerjee, Natasha Kholgade Banerjee

We introduce DeepJoin, an automated approach to generate high-resolution repairs for fractured shapes using deep neural networks. Existing approaches to perform automated shape repair operate exclusively on symmetric obj…

A Genetic Algorithm-Based Solver for Very Large Jigsaw Puzzles

2017-11-17 · CVPR 2013 6 · Dror Sholomon, Eli David, Nathan S. Netanyahu

In this paper we propose the first effective automated, genetic algorithm (GA)-based jigsaw puzzle solver. We introduce a novel procedure of merging two "parent" solutions to an improved "child" solution by detecting, ex…

Pix2Repair: Implicit Shape Restoration from Images

2023-05-29 · Xinchao Song, Nikolas Lamb, Sean Banerjee, Natasha Kholgade Banerjee

We present Pix2Repair, an automated shape repair approach that generates restoration shapes from images to repair fractured objects. Prior repair approaches require a high-resolution watertight 3D mesh of the fractured o…

Object

The Missing GAP: From Solving Square Jigsaw Puzzles to Handling Real World Archaeological Fragments

2026-05-12 · Ofir Itzhak Shahar, Gur Elkin, Ohad Ben-Shahar arxiv

Jigsaw puzzle solving has been an increasingly popular task in the computer vision research community. Recent works have utilized cutting-edge architectures and computational approaches to reassemble groups of pieces int…

DeepMend: Learning Occupancy Functions to Represent Shape for Repair

2022-10-11 · Nikolas Lamb, Sean Banerjee, Natasha Kholgade Banerjee

We present DeepMend, a novel approach to reconstruct restorations to fractured shapes using learned occupancy functions. Existing shape repair approaches predict low-resolution voxelized restorations, or require symmetri…