SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space
원문 초록
We propose a method for 3D shape reconstruction from unoriented point clouds. Our method consists of a novel SE(3)-equivariant coordinate-based network (TF-ONet), that parametrizes the occupancy field of the shape and respects the inherent symmetries of the problem. In contrast to previous shape reconstruction methods that align the input to a regular grid, we operate directly on the irregular point cloud. Our architecture leverages equivariant attention layers that operate on local tokens. This mechanism enables local shape modelling, a crucial property for scalability to large scenes. Given an unoriented, sparse, noisy point cloud as input, we produce equivariant features for each point. These serve as keys and values for the subsequent equivariant cross-attention blocks that parametrize the occupancy field. By querying an arbitrary point in space, we predict its occupancy score. We show that our method outperforms previous SO(3)-equivariant methods, as well as non-equivariant methods trained on SO(3)-augmented datasets. More importantly, local modelling together with SE(3)-equivariance create an ideal setting for SE(3) scene reconstruction. We show that by training only on single, aligned objects and without any pre-segmentation, we can reconstruct novel scenes containing arbitrarily many objects in random poses without any performance loss.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $α$-NeuS
CenterArt: Joint Shape Reconstruction and 6-DoF Grasp Estimation of Articulated Objects
ZeroShape: Regression-based Zero-shot Shape Reconstruction
Neural Poisson Surface Reconstruction: Resolution-Agnostic Shape Reconstruction from Point Clouds
Mesh Density Adaptation for Template-based Shape Reconstruction
SwIPE: Efficient and Robust Medical Image Segmentation with Implicit Patch Embeddings
토론
이 논문과 연결된 포럼 글이 아직 없습니다.