跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 10 天前AI 評分35

BrickFlow:以連接性引導從圖像重建 LEGO 積木組裝

BrickFlow: Connectivity-Guided Brick Reconstruction

AI 導讀

BrickFlow 結合以程式生成的 LEGO 組裝件預訓練、經圖像條件微調的 set-conditioned SE(3) flow 模型,以及解析式連接場引導,從組裝物件圖像推斷各零件的姿態。微調使用的數據量僅為預訓練的 1%,測試時的連接場引導則將預測拉向零件互相連接的組裝結果。研究顯示,模型規模、預訓練和引導均可改善組裝品質,模型和數據已開放供研究用途。

正文

Published on Nov 12

·

Submitted by

Kulits

on Nov 16

Authors:

Abstract

A set-conditioned SE(3) flow model pretrained on procedurally generated LEGO assemblies and finetuned with image conditioning, combined with analytic connectivity-field guidance, infers part poses to assemble objects from images.

Given a set of LEGO parts and an image of an assembled object, our task is to infer the pose of each part to assemble the object. In contrast with traditional 3D reconstruction, doing so requires satisfying discrete physical constraints, which provide structure but render the problem combinatorial and highly sensitive to small pose errors. To learn a prior over how parts fit together, we train a set-conditioned SE(3) flow model on procedurally generated assemblies. We then finetune this model to inject image conditioning, using 1% as much data. However, while the learned flow captures global structure, it does not enforce connectivity. To address this, we introduce an analytic connectivity-field guidance to pull predictions toward connected assemblies at test time. Through this, we demonstrate improved build quality with model size, pretraining, and guidance. We make our models and data available for research purposes at https://kulits.github.io/BrickFlow/

View arXiv page View PDF Project page GitHub 7 Add to collection

Get this paper in your agent:

hf papers read 2611.17321

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.17321 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.17321 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.17321 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co