Make It Flow: Animating Water in 3D Gaussian Splatting Scenes

Kjell Keune; Florian Hahlbohm; Jannis Möller; Susana Castillo; Martin Eisemann; Marcus Magnor

cs.CVOct 9, 2026

Make It Flow: Animating Water in 3D Gaussian Splatting Scenes

Authors: Kjell Keune, Florian Hahlbohm, Jannis Möller, Susana Castillo, Martin Eisemann, Marcus Magnor

Organizations: Computer Graphics Lab, TU Braunschweig, Germany

Abstract

Explicit 3D scene representations such as 3D Gaussian Splatting (3DGS) have recently enabled high-quality, real-time novel view synthesis. However, these methods assume static scenes, limiting realism in the presence of dynamic phenomena ubiquitous in real-world environments. While coherent motion (e.g., humans or vehicles) can be captured and reconstructed, high-frequency effects such as flowing water remain intractable under casual capture conditions, where dense multi-view, high-speed acquisition is not feasible. We present a method to animate water in static 3DGS scenes, enabling visually plausible motion without requiring dynamic capture or physical simulation. Our approach estimates 2D optical flow from reference images or model renderings and lifts it into a consistent 3D Eulerian motion field. We propose a cinemagraph-inspired algorithm that applies this motion field to deform Gaussian primitives, producing temporally seamless looping animations. The resulting representation retains real-time rendering performance, significantly enhances perceptual realism, and preserves free-viewpoint navigation within the scene. We evaluate our method on a newly captured dataset of in-the-wild waterfall scenes and demonstrate clear improvements over prior work in dynamic Gaussian splatting and 3D cinemagraph generation in visual quality and computational efficiency.

Figures & tables

Figure 1: We generate optical flow depicting fluid motion from multi-view observations of a static 3DGS reconstruction by refining user-defined motion hints with segmentation masks and GAN-based flow estimation. Utilizing depth renderings from the 3DGS model, we reproject optical flow into a Eulerian motion field and create seamlessly looping animations by transforming multiple instances of dynamic Gaussians using a symmetric animation technique.

Figure 2: Qualitative comparison with baselines for novel-view renderings. Our method creates a visually plausible time-consistent fluid animation, while 3D-Cinemagraphy [ LCS∗23 ] introduces artifacts, 4DGS [ YYPZ24 ] fails to capture high-frequency water motion and generates a non-plausible fluid animation, and LoopGaussian [ LCW∗24 ] creates motion that does not follow realistic fluid flow (cf. our video).

Figure 3: Qualitative comparison between LoopGaussian [ LCW∗24 ] and our method on four scenes from our dataset where we visualize scene flow by coloring Gaussians according to their current motion [ BRS∗07 ] . We show that our method creates time-consistent motion that resembles the natural flow of water, while the motion synthesized by LoopGaussian points in arbitrary directions. The results were rendered from a novel viewpoint.

Scene	#Images	Resolution	Camera	$\left\|\mathcal{G}\right\|$	$\|\mathcal{G}^{\textit{dyn}}\|$	$\left\|\mathcal{H}\right\|$
Creek	103	6223×4080	DSLR	1.59M	51K	11
Frogfall	186	6223×4080	DSLR	6.72M	26K	12
Silverfalls	67	3811×2144	Drone	5.62M	51K	10
Smallfall	74	6223×4080	DSLR	5.56M	87K	8
Town	159	6223×4080	DSLR	3.11M	12K	8
Waterfall	158	6223×4080	DSLR	5.26M	182K	14

Table 1: Properties of all dataset scenes including number of total Gaussians

\left|\mathcal{G}\right|

, dynamic Gaussians

|\mathcal{G}^{\textit{dyn}}|

and 3D motion hints

\left|\mathcal{H}\right|

Figure 4: Ground truth images along with renderings of the static and animated 3DGS reconstruction, depth renderings, dense flow hints $\mathcal{F}^{\text{dense}}_{n}$ , refined optical flow $\mathcal{F}_{n}$ , and scene flow by coloring Gaussians according to their current motion [ BRS∗07 ] . Depicted camera poses are used as closest input poses for novel-view renderings (cf. Fig. 2 and Fig. 3 ).

Figure 5: Ablation of opacity blending and state offset. We show that both techniques are required for creating a seamless loop without noticeable cuts (top) and reoccurring patterns (middle).

Figure 6: Ablation of motion field refinements. The top row shows a voxel grid visualization, and the bottom row Gaussians colored based on their current motion. By refining static regions and view hit thresholding, we can eliminate motion in static regions (left) and wrong motion (middle).

Figure 7: We show that on some scenes (top) a single directional 3D motion hint can produce nearly the same motion as many hints. On other scenes (bottom), one hint does not suffice to model the transition from a falling waterfall into a flowing river. Hints are illustrated as red lines.

	3D-Cinema.		4DGS		LoopGaussian		Ours		3DGS
Scene	VRAM	FPS	VRAM	FPS	VRAM	FPS	VRAM	FPS	VRAM	FPS
Creek	10.5 GiB	<1	2.6 GiB	431	2.1 GiB	429	1.3 GiB	457	0.9 GiB	650
Frogfall	10.8 GiB	<1	2.8 GiB	350	8.7 GiB	275	5.5 GiB	282	2.9 GiB	283
Silverfalls	13.6 GiB	<1	2.7 GiB	301	7.3 GiB	282	4.6 GiB	283	2.4 GiB	328
Smallfall	10.5 GiB	<1	2.7 GiB	430	7.2 GiB	349	4.5 GiB	342	2.3 GiB	389
Town	10.4 GiB	<1	2.6 GiB	432	4.0 GiB	409	2.5 GiB	407	1.4 GiB	569

Table 2: Quantitative comparison for rendering one animation loop.

	LoopGaussian	Ours
Scene	Total Time	Total Time	Masks	Flow	Fusion	Storage
Creek	3m42s	40s	22s	16s	2s	$5.2$ MB
Frogfall	1m55s	1m03s	38s	17s	8s	$44$ KB
Silverfalls	3m26s	37s	22s	13s	2s	$0.2$ MB
Smallfall	6m25s	28s	17s	9s	2s	$0.7$ MB
Town	1m01s	55s	33s	16s	6s	$1.1$ MB

Table 3: Quantitative comparison of motion field preprocessing. For our method, we also show storage cost and sub-task timings.

Figure 8: Our method generalizes to fluids other than water, such as lava. We show the animation from a novel camera trajectory in our video.

Figure 9: Failure case on “Weir”: inaccurate Gaussian geometry (depth, left) and a poorly reconstructed water surface (middle) lead to wrongly reprojected flow and thus an inaccurate motion field, visible as animation artifacts (right).

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Scene	initial $\|C\|$	refined $\|C\|$	refined $\rho$	average $w^{\text{view}}$	$r^{\text{view}}$
Creek	75 M	14 M	2.7 %	9	5
Frogfall	50 M	2.6 M	0.1 %	37	8
Silverfalls	70 M	0.3 M	4.7 %	12	8
Smallfall	50 M	1.4 M	3.6 %	16	7
Town	60 M	2.0 M	4.1 %	19	6
Waterfall	60 M	34 M	0.8 %	23	8

Appendix

Table 4: Properties of per scene motion fields including initial and refined number of voxels

|C|

, density

\rho

of the refined grid, average view hits per voxel

w^{\text{view}}

and view hit threshold

r^{\text{view}}

used.

Figure 10: Illustration of our symmetric animation technique for one splatted Gaussian. Forward instance $\mathcal{A}^{\text{fw}}$ (blue) and backward instance $\mathcal{A}^{\text{bw}}$ (red) are illustrated at different keyframes. Additionally, the Gaussian contour is drawn independent of Gaussian opacity, where $\mathcal{O}^{\text{fw}}$ and $\mathcal{O}^{\text{bw}}$ are plotted. The Gaussian primitive is deformed by the underlying motion field (see Sec. 3.3.1 ).

Figure 11: Ablation of Gaussian transformation. Only displacing Gaussian means with constant covariance creates noisy artifacts (top row). A small $\alpha$ (see Eq. 7 ) results in blurry unrealistic deformations (middle row), while a larger $\alpha$ creates convincing transformations following fluid motion.

Figure 12: We demonstrate the use of additional positional offset instances. While without positional offset (left) the waterfall is sparsely reconstructed, additional instances (right) create more voluminous and denser fluid regions.

3D Gaussian Splatting

3D Gaussian Splatting represents scenes as optimizable 3D Gaussian primitives for fast, photorealistic rendering from new viewpoints.

See all 1,027 papers

Eulerian Motion Reconstruction for Water Scenery
Sep 29, 2026Chuhan Chen, Yen-Chi Cheng, Ayush Saraf +84D Reconstruction 3D Reconstruction
Carnegie Mellon University · University of Illinois Urbana-Champaign · Meta
DispFlow-GS: Displacement Flow Supervision with Motion Disentangling for Monocular Deformable 3D Gaussian Splatting
Sep 29, 2026Thai Duy Nguyen, Haitian Zhang, Addison Lin Wang3D Gaussian Splatting Monocular 3D Reconstruction
Nanyang Technological University, Singapore.
AniGS: Bridging Rendering and Diffusion Prior for 3D Scene Animation
Jul 20, 2026Yen-Chi Cheng, Chen Gao, Chuhan Chen +83D Gaussian Splatting Dynamic Scene Reconstruction
University of Illinois Urbana-Champaign, Champaign-Urbana, Illinois, USA · Meta · Waymo, Bellevue, Washington, USA +2

Sep 29, 2026J/K move · Enter open · S save

Eulerian Motion Reconstruction for Water Scenery

Chuhan Chen, Yen-Chi Cheng, Ayush Saraf, Rajvi Shah+7

Carnegie Mellon University · University of Illinois Urbana-Champaign · Meta

4D Reconstruction 3D Reconstruction Dynamic Scene Reconstruction Motion Representation Learning

Open paper AskPDF arXiv

Reconstructing and animating water scenery from nature produces compelling and immersive visual experiences. Previous work examined this task from the perspective of 2D video textures, with the goal of creating a looping video. In our work, we tackle the problem from a 3D perspective, creating a looping 4D dynamic reconstruction which can be interactively rendered from novel viewpoints from a single non-looping 2D source video. We represent motion as a 3D static Eulerian motion field that advects canonical Gaussian splats that are cyclically reborn at fixed time periods, supervised using rendering losses. To model non-periodic and stochastic dynamics present in real-world scenes, we add a non-periodic, time-varying residual term to capture deviations from the static Eulerian motion field. We show quantitatively and qualitatively that our framework enables photorealistic animation of water scenes better than prior art.

Abstract

3D Gaussian Splatting

Explore similar work

Eulerian Motion Reconstruction for Water Scenery

DispFlow-GS: Displacement Flow Supervision with Motion Disentangling for Monocular Deformable 3D Gaussian Splatting

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