arXiv:2004.04485
NodeSLAM: Neural Object Descriptors for Multi-View Shape Reconstruction
원문 초록
The choice of scene representation is crucial in both the shape inference algorithms it requires and the smart applications it enables. We present efficient and optimisable multi-class learned object descriptors together with a novel probabilistic and differential rendering engine, for principled full object shape inference from one or more RGB-D images. Our framework allows for accurate and robust 3D object reconstruction which enables multiple applications including robot grasping and placing, augmented reality, and the first object-level SLAM system capable of optimising object poses and shapes jointly with camera trajectory.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations
3D Object Reconstruction with mmWave Radars
Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset
DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation
PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling
Generalizable Articulated Object Reconstruction from Casually Captured RGBD Videos
토론
이 논문과 연결된 포럼 글이 아직 없습니다.