pith. sign in

arxiv: 2301.11280 · v1 · pith:WSNOLUYYnew · submitted 2023-01-26 · 💻 cs.CV · cs.AI· cs.LG

Text-To-4D Dynamic Scene Generation

classification 💻 cs.CV cs.AIcs.LG
keywords dynamictextapproachmav3dmethodmodelscenescenes
0
0 comments X
read the original abstract

We present MAV3D (Make-A-Video3D), a method for generating three-dimensional dynamic scenes from text descriptions. Our approach uses a 4D dynamic Neural Radiance Field (NeRF), which is optimized for scene appearance, density, and motion consistency by querying a Text-to-Video (T2V) diffusion-based model. The dynamic video output generated from the provided text can be viewed from any camera location and angle, and can be composited into any 3D environment. MAV3D does not require any 3D or 4D data and the T2V model is trained only on Text-Image pairs and unlabeled videos. We demonstrate the effectiveness of our approach using comprehensive quantitative and qualitative experiments and show an improvement over previously established internal baselines. To the best of our knowledge, our method is the first to generate 3D dynamic scenes given a text description.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 15 Pith papers

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

  1. Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution

    cs.CL 2023-09 unverdicted novelty 8.0

    Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.

  2. Functionalization via Structure Completion and Motion Rectification

    cs.CV 2026-05 unverdicted novelty 7.0

    Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture wi...

  3. R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow

    cs.CV 2026-05 unverdicted novelty 7.0

    R-DMesh generates high-fidelity 4D meshes aligned to video by disentangling base mesh, motion, and a learned rectification jump offset inside a VAE, then using Triflow Attention and rectified-flow diffusion.

  4. Action Images: End-to-End Policy Learning via Multiview Video Generation

    cs.CV 2026-04 unverdicted novelty 7.0

    Action Images turn robot arm motions into interpretable multiview pixel videos, letting video backbones serve as zero-shot policies for end-to-end robot learning.

  5. Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards

    cs.CV 2026-03 unverdicted novelty 7.0

    SOLACE improves text-to-image generation by using intrinsic self-confidence rewards from noise reconstruction accuracy during reinforcement learning post-training without external supervision.

  6. PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation

    cs.CV 2026-02 unverdicted novelty 7.0

    PerpetualWonder introduces a closed-loop generative simulator with a unified physical-visual representation for long-horizon action-conditioned 4D scene generation from one image.

  7. DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation

    cs.CV 2023-09 unverdicted novelty 7.0

    DreamGaussian creates high-quality textured 3D meshes from single-view images in 2 minutes via generative Gaussian Splatting with mesh extraction and UV refinement.

  8. Helix4D: Complex 4D Mesh Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    Helix4D generates high-quality dynamic 4D meshes from videos by extending Trellis2 with sliding-window cross-frame attention anchored on the first frame and a repurposed 4D temporal encoding.

  9. R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow

    cs.CV 2026-05 unverdicted novelty 6.0

    R-DMesh proposes a VAE-based disentanglement of base mesh, motion trajectories, and rectification offset plus Triflow Attention and rectified-flow diffusion to produce 4D meshes aligned to video despite initial pose mismatch.

  10. Velox: Learning Representations of 4D Geometry and Appearance

    cs.CV 2026-05 unverdicted novelty 6.0

    Velox compresses dynamic point clouds into latent tokens that support geometry via 4D surface modeling and appearance via 3D Gaussians, showing strong results on video-to-4D generation, tracking, and image-to-4D cloth...

  11. Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations

    cs.CV 2024-12 unverdicted novelty 6.0

    A framework disentangles local joint motion from global movement, trains a 2D local generator on text-2D pairs, then fine-tunes on 3D data to output view-consistent 3D motions.

  12. R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow

    cs.CV 2026-05 unverdicted novelty 5.0

    R-DMesh uses a VAE with a learned rectification jump offset and Triflow Attention inside a rectified-flow diffusion transformer to produce video-aligned 4D meshes despite initial pose misalignment.

  13. DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation

    cs.CV 2025-09 unverdicted novelty 5.0

    LGAA is a modular adapter framework that lifts multi-view diffusion models to produce 2D Gaussian Splats with PBR channels for high-quality relightable 3D mesh extraction using data-efficient finetuning on 69k instances.

  14. AnimateAnyMesh++: A Flexible 4D Foundation Model for High-Fidelity Text-Driven Mesh Animation

    cs.CV 2026-04 unverdicted novelty 4.0

    AnimateAnyMesh++ animates arbitrary 3D meshes from text using an expanded 300K-identity DyMesh-XL dataset, a power-law topology-aware DyMeshVAE-Flex, and a variable-length rectified-flow generator to produce semantica...

  15. World Simulation with Video Foundation Models for Physical AI

    cs.CV 2025-10 unverdicted novelty 4.0

    Cosmos-Predict2.5 unifies text-to-world, image-to-world, and video-to-world generation in one model trained on 200M clips with RL post-training, delivering improved quality and control for physical AI.