PyTorchKR Papers

최신 논문

총 2편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2607.20660v1cs.CV

Axolotl3D: a Unified Framework for Faithful 3D Shape Completion

Recent 3D generative models produce high-quality geometry from a single image using large-scale priors and diffusion architectures. However, they assume complete visibility and single-view inputs, limiting applicability in multi-view, occluded, or editing scenarios. Although prior works address these challenges individually, they lack a unified framework for controllable 3D completion under diverse conditioning signals. We present Axolotl3D, a multi-modal and occlusion-aware 3D generation model that jointly conditions on images, visibility masks, camera parameters, and a partial point cloud. The point cloud serves as a geometric anchor promoting faithful shape completion, while camera parameters ensure consistent multi-view alignment in a shared 3D coordinate system. A unified training strategy synthesizes diverse conditioning regimes from large-scale 3D data, enabling robust cross-modal reasoning. Experiments on Toys4K and OmniObject3D demonstrate state-of-the-art performance under both clean and occluded settings, as well as strong results in real-world reconstruction and geometry-consistent editing.

arXiv:2607.00522v1cs.CV

Restore3D: 형상 및 텍스처 복원으로 손상된 객체에 생명 불어넣기

Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration

손상된 3D 객체의 형상과 텍스처를 다시점(multi-view) 이미지로 동시에 복원하는 프레임워크 Restore3D를 제안하며, Depth-Aware Mask Rectifier를 갖춘 Mask Self-Perceiver 모듈로 복원 영역을 자동 인식하고 coarse-to-fine 재구성 전략으로 고해상도 텍스처 3D 메시를 생성한다. 합성 및 실제 손상 객체 벤치마크에서 인페인팅, 완성, 재구성 기준 모델 대비 우수한 성능을 보였다.