4 Hits in 2.7 sec

SDM-NET: Deep Generative Network for Structured Deformable Mesh [article]

Lin Gao, Jie Yang, Tong Wu, Yu-Jie Yuan, Hongbo Fu, Yu-Kun Lai, Hao Zhang
2019 arXiv   pre-print
Our key observation is that while the overall structure of a 3D shape can be complex, the shape can usually be decomposed into a set of parts, each homeomorphic to a box, and the finer-scale geometry of  ...  Specifically, the network is trained to generate a spatial arrangement of closed, deformable mesh parts, which respect the global part structure of a shape collection, e.g., chairs, airplanes, etc.  ...  StructureNet shares much commonality with GRASS but extends it in two important ways.  ... 
arXiv:1908.04520v2 fatcat:3dmtrxswqrdkngles35y434jdu

Learning Body-Aware 3D Shape Generative Models [article]

Bryce Blinn, Alexander Ding, Daniel Ritchie, R. Kenny Jones, Srinath Sridhar, Manolis Savva
2021 arXiv   pre-print
In this paper, we learn body-aware generative models of 3D shapes.  ...  Existing data-driven generative models of 3D shapes produce plausible objects but do not reason about the relationship of those objects to the human body.  ...  Thus, physically connected and stable [20]. We extend this idea the first stage of our system is a physically-based optimiza- to human body awareness.  ... 
arXiv:2112.07022v2 fatcat:rag45srmlneclnfadq2do7iq7a

PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning [article]

Yining Hong, Li Yi, Joshua B. Tenenbaum, Antonio Torralba, Chuang Gan
2021 arXiv   pre-print
Therefore, to better serve for part-based conceptual, relational and physical reasoning, we introduce a new large-scale diagnostic visual reasoning dataset named PTR.  ...  Visual reasoning based on the full part-whole hierarchy is much more challenging than object-centric reasoning due to finer-grained concepts, richer geometry relations, and more complex physics.  ...  Sagnet: Structure-aware generative network for 3d-shape modeling.  ... 
arXiv:2112.05136v1 fatcat:h5rtliiw35fftaqfbznhpgcygu

A Revisit of Shape Editing Techniques: from the Geometric to the Neural Viewpoint [article]

Yu-Jie Yuan, Yu-Kun Lai, Tong Wu, Lin Gao, Ligang Liu
2021 arXiv   pre-print
With increasing availability of 3D shapes on the Internet, data-driven methods were proposed to improve the editing results.  ...  3D shape editing is widely used in a range of applications such as movie production, computer games and computer aided design.  ...  They utilize LBS to generate primary deformations and learn those physical behaviors from the example sequences.  ... 
arXiv:2103.01694v1 fatcat:lhgswnemnbhvrazl76qhz5rhmy