Decomposing 3d scenes into objects via unsupervised volume segmentation
We present ObSuRF, a method which turns a single image of a scene into a 3D model
represented as a set of Neural Radiance Fields (NeRFs), with each NeRF corresponding to …
represented as a set of Neural Radiance Fields (NeRFs), with each NeRF corresponding to …
Unsupervised learning of shape programs with repeatable implicit parts
Shape programs encode shape structures by representing object parts as subroutines and
constructing the overall shape by composing these subroutines. This usually involves the …
constructing the overall shape by composing these subroutines. This usually involves the …
Learning continuous implicit representation for near-periodic patterns
Abstract Near-Periodic Patterns (NPP) are ubiquitous in man-made scenes and are
composed of tiled motifs with appearance differences caused by lighting, defects, or design …
composed of tiled motifs with appearance differences caused by lighting, defects, or design …
Tree-Structured Shading Decomposition
We study inferring a tree-structured representation from a single image for object shading.
Prior work typically uses the parametric or measured representation to model shading …
Prior work typically uses the parametric or measured representation to model shading …
Multi-plane program induction with 3d box priors
We consider two important aspects in understanding and editing images: modeling regular,
program-like texture or patterns in 2D planes, and 3D posing of these planes in the scene …
program-like texture or patterns in 2D planes, and 3D posing of these planes in the scene …
Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects
Our world is full of identical objects (\emphe. g., cans of coke, cars of same model). These
duplicates, when seen together, provide additional and strong cues for us to effectively …
duplicates, when seen together, provide additional and strong cues for us to effectively …
Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations
B Dedhia, NK Jha - arXiv preprint arXiv:2403.07887, 2024 - arxiv.org
Object-centric methods have seen significant progress in unsupervised decomposition of
raw perception into rich object-like abstractions. However, limited ability to ground object …
raw perception into rich object-like abstractions. However, limited ability to ground object …
Optimal teaching curricula with compositional simplicity priors
M Garcia-Piqueras, J Hernández-Orallo - … 13–17, 2021, Proceedings, Part I …, 2021 - Springer
Abstract Machine teaching under strong simplicity priors can teach any concept in universal
languages. Remarkably, recent experiments suggest that the teaching sets are shorter than …
languages. Remarkably, recent experiments suggest that the teaching sets are shorter than …
Conditional teaching size
M Garcia-Piqueras, J Hernández-Orallo - arXiv preprint arXiv:2107.07038, 2021 - arxiv.org
Recent research in machine teaching has explored the instruction of any concept expressed
in a universal language. In this compositional context, new experimental results have shown …
in a universal language. In this compositional context, new experimental results have shown …
Learning to Infer 3D Shape Programs with Differentiable Renderer
Y Liang - arXiv preprint arXiv:2206.12675, 2022 - arxiv.org
Given everyday artifacts, such as tables and chairs, humans recognize high-level
regularities within them, such as the symmetries of a table, the repetition of its legs, while …
regularities within them, such as the symmetries of a table, the repetition of its legs, while …