https://github.com/TheoDEPRELLE/AtlasNetV2
공식 코드Learning elementary structures for 3D shape generation and matching
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Finding a meaningful correspondence between two or more shapes is one of the most fundamental shape analysis tasks. The problem can be generally stated as: given input shapes S1,S2,...,SN, find a meaningful relation (or mapping) between their elements. Under different contexts, the problem has also been referred to as registration, alignment, or simply, matching. Shape correspondence is a key algorithmic component in tasks such as 3D scan alignment and space-time reconstruction, as well as an indispensable prerequisite in diverse applications including attribute transfer, shape interpolation, and statistical modeling.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Learning elementary structures for 3D shape generation and matching
CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds
ROCA: Robust CAD Model Retrieval and Alignment from a Single Image
DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction
Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features
Learning elementary structures for 3D shape generation and matching
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.