Pith. sign in

REVIEW 47 cited by

DreamGaussian4D: Generative 4D Gaussian Splatting

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 2312.17142 v3 pith:PHMKCN6D submitted 2023-12-28 cs.CV cs.GR

Jiawei Ren , Liang Pan , Jiaxiang Tang , Chi Zhang , Ang Cao , Gang Zeng , Ziwei Liu This is my paper
classification cs.CVcs.GR
keywords generationgaussiandg4ddreamgaussian4defficientframeworkgeneratedmethods
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

4D content generation has achieved remarkable progress recently. However, existing methods suffer from long optimization times, a lack of motion controllability, and a low quality of details. In this paper, we introduce DreamGaussian4D (DG4D), an efficient 4D generation framework that builds on Gaussian Splatting (GS). Our key insight is that combining explicit modeling of spatial transformations with static GS makes an efficient and powerful representation for 4D generation. Moreover, video generation methods have the potential to offer valuable spatial-temporal priors, enhancing the high-quality 4D generation. Specifically, we propose an integral framework with two major modules: 1) Image-to-4D GS - we initially generate static GS with DreamGaussianHD, followed by HexPlane-based dynamic generation with Gaussian deformation; and 2) Video-to-Video Texture Refinement - we refine the generated UV-space texture maps and meanwhile enhance their temporal consistency by utilizing a pre-trained image-to-video diffusion model. Notably, DG4D reduces the optimization time from several hours to just a few minutes, allows the generated 3D motion to be visually controlled, and produces animated meshes that can be realistically rendered in 3D engines.

Discussion (0). Sign in to comment.

Forward citations

Cited by 47 Pith papers

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

  1. Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation

    cs.GR 2026-05 unverdicted novelty 8.0 of 10

    Rigel3D jointly generates rigged 3D meshes with geometry, skeleton topology, joint positions, and skinning weights using coupled surface and skeleton latent representations for image-conditioned animation-ready asset ...

  2. Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats

    cs.GR 2026-06 unverdicted novelty 7.0 of 10

    A Representation Abstraction Framework converts 3DGS, meshes, and fluids into unified particles for scene-level heterogeneous multi-solver physics simulation.

  3. PhysAgent: Automating Physics-Based 4D Synthesis via Trajectory-Grounded Multi-Agent Feedback

    cs.RO 2026-06 unverdicted novelty 7.0 of 10

    PhysAgent is a simulator-in-the-loop multi-agent system that automates physically grounded 4D synthesis from multimodal prompts by using trajectory feedback from vision models and LLM reasoning to optimize force fields.

  4. Functionalization via Structure Completion and Motion Rectification

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    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...

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

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    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.

  6. AniGen: Unified $S^3$ Fields for Animatable 3D Asset Generation

    cs.GR 2026-04 unverdicted novelty 7.0 of 10

    AniGen directly generates animatable 3D assets with consistent shape, skeleton, and skinning from single images using unified S^3 fields and a two-stage flow-matching pipeline.

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

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    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.

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

    cs.CV 2026-02 unverdicted novelty 7.0 of 10

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

  9. UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models

    cs.CV 2025-04 unverdicted novelty 7.0 of 10

    UniEdit-Flow presents tuning-free Uni-Inv and Uni-Edit methods for inversion and editing in flow models that achieve accurate reconstruction and robust region-preserving edits across generative models.

  10. 4DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A diffusion model trained on 60,000 fitted 4D Gaussian Splatting human clips generates text-prompted, view-consistent dynamic humans directly in 4D, over 10x faster than video-first pipelines.

  11. AniGS: Bridging Rendering and Diffusion Prior for 3D Scene Animation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    AniGS animates a static 3D Gaussian Splatting scene by iteratively distilling video-diffusion motion into a time-conditioned deformation field while keeping static regions fixed.

  12. 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.

  13. SkelGen4D: Weakly-Supervised Skeleton-Based 4D Generation for Text-Driven Mesh Animation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Weakly supervised fitting recovers consistent pseudo-skeletons from mesh sequences, then a text-conditioned transformer with Motion-GRPO generates editable skeleton-driven 4D mesh animations.

  14. Alignment Is All You Need For X-to-4D Generation

    cs.CV 2026-07 unverdicted novelty 6.0 of 10

    Align4D introduces object distance alignment, motion-geometry joint alignment, asynchronous optimization, and the X4D dataset to achieve state-of-the-art X-to-4D generation from multimodal inputs.

  15. SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation

    cs.AI 2026-07 unverdicted novelty 6.0 of 10

    SimWorlds presents a multi-agent system with planner-coder-reviewer workflow, layered scene protocol, and runtime inspection tools to create dynamic 4D scenes from text, plus the 4DBuildBench benchmark showing outperf...

  16. Feed-forward Motion In-betweening for Any 4D

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    Proposes a feed-forward keyframe-conditioned in-betweening method for arbitrary 4D meshes using a topology-agnostic VAE and MMDiT-based rectified flow model.

  17. DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    DynaTok introduces a token-based framework for correspondence-free 4D reconstruction from partial point cloud sequences via latent encoding, transformer aggregation, residual decoupling, and flow-matching decoding.

  18. PointAction: 3D Points as Universal Action Representations for Robot Control

    cs.RO 2026-06 unverdicted novelty 6.0 of 10

    PointAction uses predicted dynamic 3D pointmaps from fine-tuned video models as an embodiment-agnostic action representation to map video predictions to executable robot actions.

  19. PhyGenHOI: Physically-Aware 4D Generation of Dynamic Human-Object Interactions

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    PhyGenHOI couples a motion diffusion model for humans with material point method simulation for objects on 3D Gaussians, using attraction loss, contact re-simulation, and masked video-SDS to produce physically consist...

  20. Helix4D: Complex 4D Mesh Generation

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    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.

  21. Variance Reduction for Expectations with Diffusion Teachers

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-o...

  22. Fast 4D Mesh Generation by Spatio-Temporal Attention Chains

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    A training-free Spatio-Temporal Attention Chain framework accelerates 4D mesh generation 13x, improves quality, scales to 16x longer videos, and supports downstream tracking and camera estimation.

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

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    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.

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

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    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...

  25. Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    Sculpt4D generates temporally coherent 4D shapes by integrating a block sparse attention mechanism with time-decaying mask into a pretrained 3D diffusion transformer, achieving SOTA results with 56% less computation.

  26. Scene-Agnostic Object-Centric Representation Learning for 3D Gaussian Splatting

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    A scene-agnostic object codebook learned via unsupervised object-centric learning provides consistent identity-anchored representations for 3D Gaussians across multiple scenes.

  27. MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation

    cs.CV 2026-02 conditional novelty 6.0 of 10

    A geometry-consistent multi-view RGBD 4D world model for robot manipulation, whose actions are recovered by test-time optimization of a learned trajectory latent, outperforming single- and dual-view world-model baseli...

  28. SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation

    cs.RO 2026-02 conditional novelty 6.0 of 10

    SoMA couples robot joint actions, environmental forces, and learned Gaussian-splat dynamics into a single neural simulator, improving resimulation and generalization on real robot soft-body manipulation by about 20% o...

  29. Hyper Diffusion Avatars: Dynamic Human Avatar Generation using Network Weight Space Diffusion

    cs.GR 2025-09 conditional novelty 6.0 of 10

    A diffusion model over per-person UNet weights generates new dynamic human avatars that render pose-dependent 3D Gaussians in real time.

  30. CharacterShot: Controllable and Consistent 4D Character Animation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A new pipeline generates pose-controlled, view-consistent 4D character animations from one reference image and a 2D pose sequence, backed by a new 13,115-character dataset and benchmark.

  31. 4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A two-stage cascaded video diffusion model generates 16-view consistent videos from a monocular video, enabling higher-quality 4D content reconstruction.

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

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Hallo4D mitigates 3D/4D generation hallucinations via LMM-based detection, multi-model voting correction, and motion-aware optimization without retraining base generators.

  33. CP4D: Compositional Physics-aware 4D Scene Generation

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    CP4D generates physically consistent 4D scenes via compositional integration of pre-trained 3D models, hybrid simulator-diffusion motion synthesis, and automated scene composition.

  34. SkelMo: Universal Skeletal Motion Generation for 3D Rigged Shapes

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    MotionDreamer is a diffusion framework for category-agnostic skeletal motion generation from 2D videos, trained on a curated 20k rigged model dataset with a structural-semantic injection mechanism.

  35. SkelMo: Universal Skeletal Motion Generation for 3D Rigged Shapes

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    SkelMo introduces a category-agnostic diffusion framework for skeletal motion generation from 2D videos, trained on a new dataset of ~20,000 rigged 3D animations with a structural-semantic injection mechanism.

  36. Variance Reduction for Expectations with Diffusion Teachers

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    CARV introduces a hierarchical Monte Carlo estimator with amortized reuse, importance sampling, and stratification that yields 2-3x effective compute gains on diffusion-teacher pipelines while cutting gradient varianc...

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

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    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.

  38. RoDyn: Taming Interactive Robot-Dynamic 2.5D World Model for Robotic Manipulation

    cs.RO 2025-10 unverdicted novelty 5.0 of 10

    Abstract describes RoDyn but full text describes iMoWM; the record is internally inconsistent and the headline claims are absent from the body.

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

    cs.CV 2025-09 unverdicted novelty 5.0 of 10

    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.

  40. Align 3D Representation and Text Embedding for 3D Content Personalization

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    Invert3D projects 3D content into a CLIP-style text-aligned embedding, allowing text-prompt personalization without per-scene retraining.

  41. DIP-GS: Deep Image Prior For Gaussian Splatting Sparse View Recovery

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    DIP-GS applies a deep image prior in a coarse-to-fine manner to enable 3D Gaussian Splatting for sparse-view reconstruction.

  42. LIVE-GS: LLM Powers Interactive VR Experience with Physics-Aware Gaussian Splatting

    cs.HC 2024-12 unverdicted novelty 5.0 of 10

    LIVE-GS uses an LLM to predict physical parameters from static Gaussian assets in 10 seconds for physics-aware VR interactions, validated by interviews, baseline comparisons, and user studies.

  43. 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.

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

    cs.CV 2026-04 unverdicted novelty 4.0 of 10

    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...

  45. Advances in 4D Representation: Geometry, Motion, and Interaction

    cs.CV 2025-10 conditional novelty 4.0 of 10

    A representation-centric survey of 4D generation and reconstruction, organized by geometry, motion, and interaction, with qualitative trade-off comparisons across seven representation families.

  46. DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes

    cs.CV 2025-08 conditional novelty 4.0 of 10

    DrivingGaussian++ reconstructs dynamic surround-view driving scenes and performs training-free multi-task editing (weather, texture, object manipulation) using Gaussians, diffusion models, and LLM-generated trajectories.

  47. A Survey on 3D Gaussian Splatting

    cs.CV 2024-01 unverdicted novelty 2.0 of 10

    A survey compiling principles, applications, benchmarks, and challenges of 3D Gaussian Splatting for explicit 3D scene representation.

Pith tools