Compositional 3D Scene Generation using Locally Conditioned Diffusion
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:UAQFXHMSrecord.jsonopen to challenge →
read the original abstract
Designing complex 3D scenes has been a tedious, manual process requiring domain expertise. Emerging text-to-3D generative models show great promise for making this task more intuitive, but existing approaches are limited to object-level generation. We introduce \textbf{locally conditioned diffusion} as an approach to compositional scene diffusion, providing control over semantic parts using text prompts and bounding boxes while ensuring seamless transitions between these parts. We demonstrate a score distillation sampling--based text-to-3D synthesis pipeline that enables compositional 3D scene generation at a higher fidelity than relevant baselines.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
Learning Interactive Real-World Simulators
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
-
SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion
SynCity 3000 generates large, coherent 3D scenes from text by fine-tuning an image-to-3D diffusion model to operate convolutionally on overlapping windows, trained on procedurally generated synthetic scene data.
-
CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation
CamCo equips image-to-video generators with Plücker-coordinate camera inputs and epipolar attention to improve 3D consistency and camera controllability.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.