AutoRecon：自動化 3D 物體發現與重建

摘要

對於數位內容創作，一個完全自動化的物體重建流程至關重要。儘管3D重建領域已經取得了深刻的發展，但為了獲得乾淨的物體模型，仍然依賴不同形式的人工勞動，如邊界框標記、遮罩註釋和網格操作等。本文提出了一個名為AutoRecon的新型框架，用於從多視角影像中自動發現和重建物體。我們展示了如何通過利用自監督2D視覺Transformer特徵，從SfM點雲中強健地定位和分割前景物體。然後，我們通過分解的點雲提供的密集監督，重建神經場景表示，實現準確的物體重建和分割。在DTU、BlendedMVS和CO3D-V2數據集上的實驗證明了AutoRecon的有效性和穩健性。

English

A fully automated object reconstruction pipeline is crucial for digital content creation. While the area of 3D reconstruction has witnessed profound developments, the removal of background to obtain a clean object model still relies on different forms of manual labor, such as bounding box labeling, mask annotations, and mesh manipulations. In this paper, we propose a novel framework named AutoRecon for the automated discovery and reconstruction of an object from multi-view images. We demonstrate that foreground objects can be robustly located and segmented from SfM point clouds by leveraging self-supervised 2D vision transformer features. Then, we reconstruct decomposed neural scene representations with dense supervision provided by the decomposed point clouds, resulting in accurate object reconstruction and segmentation. Experiments on the DTU, BlendedMVS and CO3D-V2 datasets demonstrate the effectiveness and robustness of AutoRecon.

AutoRecon：自動化 3D 物體發現與重建

AutoRecon: Automated 3D Object Discovery and Reconstruction

摘要

Support