Pith. sign in

REVIEW 13 cited by

GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation

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 2403.12365 v2 pith:TKS6QK67 submitted 2024-03-19 cs.CV

Quankai Gao , Qiangeng Xu , Zhe Cao , Ben Mildenhall , Wenchao Ma , Le Chen , Danhang Tang , Ulrich Neumann This is my paper
classification cs.CV
keywords gaussiandynamicssplattingflowgenerationmethodnovelcontent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Creating 4D fields of Gaussian Splatting from images or videos is a challenging task due to its under-constrained nature. While the optimization can draw photometric reference from the input videos or be regulated by generative models, directly supervising Gaussian motions remains underexplored. In this paper, we introduce a novel concept, Gaussian flow, which connects the dynamics of 3D Gaussians and pixel velocities between consecutive frames. The Gaussian flow can be efficiently obtained by splatting Gaussian dynamics into the image space. This differentiable process enables direct dynamic supervision from optical flow. Our method significantly benefits 4D dynamic content generation and 4D novel view synthesis with Gaussian Splatting, especially for contents with rich motions that are hard to be handled by existing methods. The common color drifting issue that happens in 4D generation is also resolved with improved Guassian dynamics. Superior visual quality on extensive experiments demonstrates our method's effectiveness. Quantitative and qualitative evaluations show that our method achieves state-of-the-art results on both tasks of 4D generation and 4D novel view synthesis. Project page: https://zerg-overmind.github.io/GaussianFlow.github.io/

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

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

  1. ASTRA: Asynchronous Spatio-Temporal Reconstruction via Trajectory Alignment

    cs.CV 2026-08 conditional novelty 7.0 of 10

    ASTRA jointly estimates camera time offsets and dynamic Gaussian geometry by aligning projected 3D motion with observed 2D trajectory tracks, improving robustness to large asynchrony.

  2. ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction

    cs.GR 2025-09 reject novelty 7.0 of 10

    ContraGS trains 3D Gaussian Splatting directly on codebook-compressed representations, cutting peak model memory ~3.5x with small quality loss.

  3. UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models

    cs.CV 2026-08 conditional novelty 6.0 of 10

    UniWorld-View couples an occlusion-aware point cloud renderer with a dual-stream video diffusion model to synthesize large-baseline novel views from monocular video.

  4. 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.

  5. 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.

  6. AsySplat: Efficient Asymmetric 3D Gaussian Splatting for Long-Sequence Scene Modeling

    cs.CV 2026-07 accept novelty 6.0 of 10

    An asymmetric geometry-appearance architecture for generalizable 3DGS reallocates computation so smaller models match optimization-based NVS quality at ~800× speedup on 32-view 960P inputs while improving zero-shot results.

  7. VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A training-only Gaussian splatting loss, which renders predicted 3D semantics and motion into 2D camera views, improves semantic occupancy and scene flow prediction across several camera-based models.

  8. Enhanced Velocity Field Modeling for Gaussian Video Reconstruction

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Velocity field rendering with flow-based losses and flow-assisted densification lifts dynamic Gaussian novel-view PSNR by about 2.5 dB on Nvidia-long and Neu3D.

  9. EndoFlow-SLAM: Real-Time Endoscopic SLAM with Flow-Constrained Gaussian Splatting

    cs.CV 2025-06 conditional novelty 5.0 of 10

    EndoFlow-SLAM couples 3D Gaussian Splatting with optical-flow and depth-gradient supervision, and reports improved pose and rendering accuracy on static and dynamic endoscopic datasets.

  10. Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A test-time optimization method that jointly fits deformable per-object 3D Gaussians with object-centric diffusion priors to generate 4D scenes and point tracks from monocular multi-object videos.

  11. CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting

    cs.CV 2025-05 conditional novelty 5.0 of 10

    CCL-LGS improves 3D open-vocabulary semantic segmentation by adding SAM2-based cross-view mask association and contrastive codebook learning to 3D Gaussian splatting.

  12. 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.

  13. Dynamic View Synthesis as an Inverse Problem

    cs.CV 2025-06 reject novelty 3.0 of 10

    Dynamic view synthesis from a monocular video is achieved by redesigning the noise initialization of a pretrained video diffusion model using a recursive interpolation and a stochastic latent modulation.

Pith tools