Pith. sign in

REVIEW 12 cited by

Comp4D: LLM-Guided Compositional 4D Scene Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2403.16993 v1 pith:3D5HRLFL submitted 2024-03-25 cs.CV

Dejia Xu , Hanwen Liang , Neel P. Bhatt , Hezhen Hu , Hanxue Liang , Konstantinos N. Plataniotis , Zhangyang Wang This is my paper · ORCID
classification cs.CV
keywords scenecompositionalcomp4dcontentgenerationmodelsconstructscreation
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recent advancements in diffusion models for 2D and 3D content creation have sparked a surge of interest in generating 4D content. However, the scarcity of 3D scene datasets constrains current methodologies to primarily object-centric generation. To overcome this limitation, we present Comp4D, a novel framework for Compositional 4D Generation. Unlike conventional methods that generate a singular 4D representation of the entire scene, Comp4D innovatively constructs each 4D object within the scene separately. Utilizing Large Language Models (LLMs), the framework begins by decomposing an input text prompt into distinct entities and maps out their trajectories. It then constructs the compositional 4D scene by accurately positioning these objects along their designated paths. To refine the scene, our method employs a compositional score distillation technique guided by the pre-defined trajectories, utilizing pre-trained diffusion models across text-to-image, text-to-video, and text-to-3D domains. Extensive experiments demonstrate our outstanding 4D content creation capability compared to prior arts, showcasing superior visual quality, motion fidelity, and enhanced object interactions.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Wonderland: Navigating 3D Scenes from a Single Image

    cs.CV 2024-12 conditional novelty 7.0 of 10

    A feed-forward pipeline reconstructs 3D Gaussian scenes from single images by regressing 3DGS directly from camera-conditioned video diffusion latents.

  2. GS-Agent: Creating 4D Physical Worlds With Generative Simulation

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Three LLM agents write physics-engine code from text, review rendered frames, and correct errors, turning prompts into physically simulated 4D worlds with camera control.

  3. Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Hallo4D uses vision-language models to detect and correct spatial and temporal mistakes in AI-generated 3D and 4D content, improving consistency without retraining the base generators.

  4. Compositional Generative Model of Unbounded 4D Cities

    cs.CV 2025-01 conditional novelty 6.0 of 10

    CityDreamer4D is a compositional generative model that creates unbounded, temporally coherent 4D cities by separately generating static scenes, buildings, and vehicles with neural fields.

  5. DreamDrive: Generative 4D Scene Modeling from Street View Images

    cs.CV 2024-12 conditional novelty 6.0 of 10

    DreamDrive generates 3D-consistent driving videos from a single image by lifting diffusion-generated reference frames into a hybrid static and dynamic 4D Gaussian scene.

  6. AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers

    cs.CV 2024-11 conditional novelty 6.0 of 10

    AC3D improves camera control in video diffusion transformers by conditioning only early denoising steps and the first 8 of 32 blocks, and by adding 20K static-camera dynamic videos to training.

  7. TiP4GEN: Text to Immersive Panorama 4D Scene Generation

    cs.CV 2025-08 conditional novelty 5.0 of 10

    TiP4GEN generates motion-rich, geometry-consistent 360-degree 4D scenes from a global text prompt plus four local perspective prompts, using a dual-branch video diffusion model with bidirectional cross-attention and a...

  8. TextMesh4D: Zero-shot Text-to-4D Mesh Generation

    cs.CV 2025-06 conditional novelty 5.0 of 10

    TextMesh4D generates text-conditioned dynamic meshes by combining a Jacobian Deformation Field, video score distillation, and a local-global semantic regularizer in a zero-shot pipeline.

  9. Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of Experts

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A sparse mixture-of-experts 3D multimodal LLM adaptively fuses RGB, RGBD, BEV, point cloud, and voxel tokens, achieving SOTA on several ScanNet-based 3D scene understanding benchmarks.

  10. PaintScene4D: Consistent 4D Scene Generation from Text Prompts

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A training-free pipeline that turns one text-to-video clip into a multi-view 4D scene renderable along user-chosen camera paths.

  11. From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence

    cs.RO 2026-07 conditional novelty 4.0 of 10

    Physical intelligence needs an embodied brain that reasons over interventions and emits capability requests, grounded by a physical harness and shared experience contracts rather than direct actuator policies.

  12. 3D Scene Generation: A Survey

    cs.CV 2025-05 conditional

    The paper surveys 3D scene generation and organizes methods into four paradigms, with datasets, evaluation metrics, applications, and future directions.

Pith tools