Layoutgpt: Compositional visual planning and generation with large language models
Attaining a high degree of user controllability in visual generation often requires intricate,
fine-grained inputs like layouts. However, such inputs impose a substantial burden on users …
fine-grained inputs like layouts. However, such inputs impose a substantial burden on users …
Gaudi: A neural architect for immersive 3d scene generation
We introduce GAUDI, a generative model capable of capturing the distribution of complex
and realistic 3D scenes that can be rendered immersively from a moving camera. We tackle …
and realistic 3D scenes that can be rendered immersively from a moving camera. We tackle …
Layoutdm: Discrete diffusion model for controllable layout generation
Controllable layout generation aims at synthesizing plausible arrangement of element
bounding boxes with optional constraints, such as type or position of a specific element. In …
bounding boxes with optional constraints, such as type or position of a specific element. In …
MIME: Human-aware 3D scene generation
Generating realistic 3D worlds occupied by moving humans has many applications in
games, architecture, and synthetic data creation. But generating such scenes is expensive …
games, architecture, and synthetic data creation. But generating such scenes is expensive …
Citydreamer: Compositional generative model of unbounded 3d cities
Abstract 3D city generation is a desirable yet challenging task since humans are more
sensitive to structural distortions in urban environments. Additionally generating 3D cities is …
sensitive to structural distortions in urban environments. Additionally generating 3D cities is …
Lego-net: Learning regular rearrangements of objects in rooms
Humans universally dislike the task of cleaning up a messy room. If machines were to help
us with this task, they must understand human criteria for regular arrangements, such as …
us with this task, they must understand human criteria for regular arrangements, such as …
Cc3d: Layout-conditioned generation of compositional 3d scenes
In this work, we introduce CC3D, a conditional generative model that synthesizes complex
3D scenes conditioned on 2D semantic scene layouts, trained using single-view images …
3D scenes conditioned on 2D semantic scene layouts, trained using single-view images …
Sparks of large audio models: A survey and outlook
This survey paper provides a comprehensive overview of the recent advancements and
challenges in applying large language models to the field of audio signal processing. Audio …
challenges in applying large language models to the field of audio signal processing. Audio …
3dilg: Irregular latent grids for 3d generative modeling
We propose a new representation for encoding 3D shapes as neural fields. The
representation is designed to be compatible with the transformer architecture and to benefit …
representation is designed to be compatible with the transformer architecture and to benefit …
Scenedreamer: Unbounded 3d scene generation from 2d image collections
In this work, we present SceneDreamer, an unconditional generative model for unbounded
3D scenes, which synthesizes large-scale 3D landscapes from random noise. Our …
3D scenes, which synthesizes large-scale 3D landscapes from random noise. Our …