Paper page - Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocation

Source: https://huggingface.co/papers/2606.22197 Published on Jun 20

·

Submitted byhttps://huggingface.co/BatofGo

Rayon Jun 24

Abstract

Multi4D addresses the trade-off between motion consistency and visual fidelity in dynamic 3D Gaussian splatting through a multi-level competitive allocation framework that enables adaptive specialization and efficient representation.

Dynamic 3D Gaussian splattingfaces a fundamental tension betweenmotion consistencyandvisual fidelity.Deformation-based approachespreservetemporal correspondencebut suffer frommotion over-factorization,oversmoothinghigh-frequency dynamics. In contrast,4D-primitive methodscapture fine visual details yet incurtemporal overparameterization, breakingobject identityand leading to severestorage overhead. To resolve this, we introduce Multi4D, a framework for high-fidelity dynamic Gaussian Splatting based onmulti-level competitive allocation. Instead of a monolithic representation, we distribute modeling capacity across three structured levels:static structure,persistent dynamic geometry, andtransient appearance primitives. Through sharedrasterizationandresidual-driven optimization, these levels dynamically compete to explainphotometric error, enablingadaptive specializationwithout pre-assigned decomposition. This allocation preserves long-termmotion consistencywhile capturing fine dynamic detail, achievingstate-of-the-art rendering qualityandreal-time performancewith significantly fewer dynamic primitives. Furthermore, because our representation explicitly tracks compact persistent Gaussians over time, semantic features can be embedded afterward, enabling Multi4D to achieve state-of-the-art4D segmentation accuracywith an order-of-magnitude speedup. Project page: https://batfacewayne.github.io/Multi4D.io/

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2606\.22197

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.22197 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.22197 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.22197 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.