REVIEW 4 cited by
WorldCraft: Photo-Realistic 3D World Creation and Customization via LLM Agents
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Constructing photorealistic virtual worlds has applications across various fields, but it often requires the extensive labor of highly trained professionals to operate conventional 3D modeling software. To democratize this process, we introduce WorldCraft, a system where large language model (LLM) agents leverage procedural generation to create indoor and outdoor scenes populated with objects, allowing users to control individual object attributes and the scene layout using intuitive natural language commands. In our framework, a coordinator agent manages the overall process and works with two specialized LLM agents to complete the scene creation: ForgeIt, which integrates an ever-growing manual through auto-verification to enable precise customization of individual objects, and ArrangeIt, which formulates hierarchical optimization problems to achieve a layout that balances ergonomic and aesthetic considerations. Additionally, our pipeline incorporates a trajectory control agent, allowing users to animate the scene and operate the camera through natural language interactions. Our system is also compatible with off-the-shelf deep 3D generators to enrich scene assets. Through evaluations and comparisons with state-of-the-art methods, we demonstrate the versatility of WorldCraft, ranging from single-object customization to intricate, large-scale interior and exterior scene designs. This system empowers non-professionals to bring their creative visions to life.
Forward citations
Cited by 4 Pith papers
-
IDEAL-Bench: Indoor Dataset and Evaluation suite for Analyzing 3D Layout reasoning
Current VLMs top out at 62.1/100 on holistic single-image 3D indoor layout prediction, with strong recognition but weak geometric regression, and mid-tier rankings that shift relative to QA and primitive-reconstructio...
-
CinemaTraj: Composing Atomic Camera Trajectories for 3D Scenes with LLM Agents
An LLM agent grounded in a 3D scene graph composes parametric cinematic camera moves and SDF-optimizes them into prompt-faithful, collision-free trajectories on ScanNet++.
-
Sat2RealCity: Geometry-Aware and Appearance-Controllable 3D Urban Generation from Satellite Imagery
A satellite-to-3D-city pipeline that generates building entities with OSM geometry priors and MLLM/T2I appearance guidance reports strong gains over existing city-generation baselines.
-
Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion
Sat2City generates explicit 3D city geometry and appearance from a height-map condition using cascaded latent diffusion on sparse voxel grids, beating prior methods on a new synthetic city dataset.
Discussion (0). Continue with ORCID to comment.