paper-with-me

홈 › Papers

Extending DeepSDF for automatic 3D shape retrieval and similarity transform estimation

2020-04-20 · Oladapo Afolabi, Allen Y. Yang, S. Shankar Sastry

Recent advances in computer graphics and computer vision have found successful application of deep neural network models for 3D shapes based on signed distance functions (SDFs) that are useful for shape representation, retrieval, and completion. However, this approach has been limited by the need to have query shapes in the same canonical scale and pose as those observed during training, restricting its effectiveness on real world scenes. We present a formulation to overcome this issue by jointly estimating shape and similarity transform parameters. We conduct experiments to demonstrate the effectiveness of this formulation on synthetic and real datasets and report favorable comparisons to the state of the art. Finally, we also emphasize the viability of this approach as a form of 3D model compression.

📄 PDF Abstract BibTeX arXiv:2004.09048

Code (0)

등록된 구현이 없습니다.

Tasks

3D Shape Classification3D Shape RetrievalModel CompressionRetrieval

Similar Papers 제목 키워드 기반

Curriculum DeepSDF

2020-03-19 · ECCV 2020 8 · Yueqi Duan, Haidong Zhu, He Wang, Li Yi 외

When learning to sketch, beginners start with simple and flexible shapes, and then gradually strive for more complex and accurate ones in the subsequent training sessions. In this paper, we design a "shape curriculum" fo…

3D Shape RepresentationRepresentation Learning

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

2019-01-16 · CVPR 2019 6 · Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe 외

Computer graphics, 3D computer vision and robotics communities have produced multiple approaches to representing 3D geometry for rendering and reconstruction. These provide trade-offs across fidelity, efficiency and comp…

3D geometry3D Reconstruction3D Shape Representation

3D Shapes Local Geometry Codes Learning with SDF

2021-08-19 · Shun Yao, Fei Yang, Yongmei Cheng, Mikhail G. Mozerov

A signed distance function (SDF) as the 3D shape description is one of the most effective approaches to represent 3D geometry for rendering and reconstruction. Our work is inspired by the state-of-the-art method DeepSDF …

3D geometry3D Shape ReconstructionGraph Neural Network

Shallow Signed Distance Functions for Kinematic Collision Bodies

2024-11-11 · Osman Akar, Yushan Han, Yizhou Chen, Weixian Lan 외

We present learning-based implicit shape representations designed for real-time avatar collision queries arising in the simulation of clothing. Signed distance functions (SDFs) have been used for such queries for many ye…

Computational Efficiency

Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction

2020-03-24 · ECCV 2020 8 · Rohan Chabra, Jan Eric Lenssen, Eddy Ilg, Tanner Schmidt 외

Efficiently reconstructing complex and intricate surfaces at scale is a long-standing goal in machine perception. To address this problem we introduce Deep Local Shapes (DeepLS), a deep shape representation that enables …

3D ReconstructionSurface Reconstruction