paper-with-me

Papers

XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

2023-12-06 · CVPR 2024 1 · Xuanchi Ren, Jiahui Huang, Xiaohui Zeng, Ken Museth, Sanja Fidler, Francis Williams

We present XCube (abbreviated as $\mathcal{X}^3$), a novel generative model for high-resolution sparse 3D voxel grids with arbitrary attributes. Our model can generate millions of voxels with a finest effective resolution of up to $1024^3$ in a feed-forward fashion without time-consuming test-time optimization. To achieve this, we employ a hierarchical voxel latent diffusion model which generates progressively higher resolution grids in a coarse-to-fine manner using a custom framework built on the highly efficient VDB data structure. Apart from generating high-resolution objects, we demonstrate the effectiveness of XCube on large outdoor scenes at scales of 100m$\times$100m with a voxel size as small as 10cm. We observe clear qualitative and quantitative improvements over past approaches. In addition to unconditional generation, we show that our model can be used to solve a variety of tasks such as user-guided editing, scene completion from a single scan, and text-to-3D. The source code and more results can be found at https://research.nvidia.com/labs/toronto-ai/xcube/.

📄 PDF Abstract BibTeX arXiv:2312.03806

Code (1)

nv-tlabs/XCube 공식 구현 pytorch

Tasks

3D Shape GenerationScene GenerationText to 3D

Methods 이 논문이 사용한 방법론

Sparse Convolutions 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Latent Diffusion Model Diffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.

Similar Papers 제목 키워드 기반

Mining Reaction and Diffusion Dynamics in Social Activities

2022-08-07 · Taichi Murayama, Yasuko Matsubara, Yasushi Sakurai

Large quantifies of online user activity data, such as weekly web search volumes, which co-evolve with the mutual influence of several queries and locations, serve as an important social sensor. It is an important task t…

When Tom Eats Kimchi: Evaluating Cultural Bias of Multimodal Large Language Models in Cultural Mixture Contexts

2025-03-21 · Jun Seong Kim, Kyaw Ye Thu, Javad Ismayilzada, Junyeong Park 외

In a highly globalized world, it is important for multi-modal large language models (MLLMs) to recognize and respond correctly to mixed-cultural inputs. For example, a model should correctly identify kimchi (Korean food)…

Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling

2023-01-09 · Keyu Tian, Yi Jiang, Qishuai Diao, Chen Lin 외

We identify and overcome two key obstacles in extending the success of BERT-style pre-training, or the masked image modeling, to convolutional networks (convnets): (i) convolution operation cannot handle irregular, rando…

2D Object DetectionContrastive LearningDecoderImage Classification+5

HySparK: Hybrid Sparse Masking for Large Scale Medical Image Pre-Training

2024-08-11 · Fenghe Tang, Ronghao Xu, Qingsong Yao, Xueming Fu 외

The generative self-supervised learning strategy exhibits remarkable learning representational capabilities. However, there is limited attention to end-to-end pre-training methods based on a hybrid architecture of CNN an…

DecoderSelf-Supervised Learning

Multi-scale Generative Modeling for Fast Sampling

2024-11-14 · Xiongye Xiao, Shixuan Li, Luzhe Huang, Gengshuo Liu 외

While working within the spatial domain can pose problems associated with ill-conditioned scores caused by power-law decay, recent advances in diffusion-based generative models have shown that transitioning to the wavele…