BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information

Rueegg, Nadine; Schindler, Konrad; Black, Michael J.

doi:10.48550/arxiv.2203.15536

Cited by 1 publication

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One is to reconstruct using a whole model, the other is to use a primitive-composed model. As for the former, one common method is to fit the input or regress the parameters of a 3D deformable template model (Zuffi, Kanazawa, and Black 2018;Zuffi et al 2019;Rueegg et al 2022;Li et al 2020;Dwivedi et al 2022;Zhang et al 2021bZhang et al , 2023, which is usually category-specific. The other is to encode the model into a latent manifold and then decode the latent code into the model (Park et al 2019;Sitzmann, Zollhöfer, and Wetzstein 2020;Wu et al 2017Wu et al , 2023Huang et al 2023).…”

Section: Related Workmentioning

confidence: 99%

Primitive-Based 3D Human-Object Interaction Modelling and Programming

Liu,

Li,

Fang

et al. 2024

AAAI

View full text Add to dashboard Cite

Embedding Human and Articulated Object Interaction (HAOI) in 3D is an important direction for a deeper human activity understanding. Different from previous works that use parametric and CAD models to represent humans and objects, in this work, we propose a novel 3D geometric primitive-based language to encode both humans and objects. Given our new paradigm, humans and objects are all compositions of primitives instead of heterogeneous entities. Thus, mutual information learning may be achieved between the limited 3D data of humans and different object categories. Moreover, considering the simplicity of the expression and the richness of the information it contains, we choose the superquadric as the primitive representation. To explore an effective embedding of HAOI for the machine, we build a new benchmark on 3D HAOI consisting of primitives together with their images and propose a task requiring machines to recover 3D HAOI using primitives from images. Moreover, we propose a baseline of single-view 3D reconstruction on HAOI. We believe this primitive-based 3D HAOI representation would pave the way for 3D HAOI studies. Our code and data are available at https://mvig-rhos.com/p3haoi.

show abstract