Hugging Face Trending Papers
Make It Flow: Animating Water in 3D Gaussian Splatting Scenes
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computer Vision
2d ago
Make It Flow: Animating Water in 3D Gaussian Splatting Scenes
arXiv:2610.13860v1 Announce Type: new Abstract: Explicit 3D scene representations such as 3D Gaussian Splatting (3DGS) have recently enabled high-quality, real-time novel view synthesis. However, the...
arXiv Computer Vision
Oct 1
Eulerian Motion Reconstruction for Water Scenery
arXiv:2609.38622v1 Announce Type: new Abstract: Reconstructing and animating water scenery from nature produces compelling and immersive visual experiences. Previous work examined this task from the...
Hugging Face Trending Papers
Jul 20
AniGS: Bridging Rendering and Diffusion Prior for 3D Scene Animation
Novel view rendering of large and complex reconstructed scenes is becoming increasingly photorealistic. However, most reconstructions remain static and lack the ambient motion that makes environments immersive.
arXiv Computer Vision
Sep 30
DispFlow-GS: Displacement Flow Supervision with Motion Disentangling for Monocular Deformable 3D Gaussian Splatting
arXiv:2609.36940v1 Announce Type: new Abstract: Accurate dynamic scene reconstruction is important for robotic perception, where temporally consistent representations of dynamic environments are esse...
Hugging Face Trending Papers
Aug 24
AquaFlow: A Monocular Gaussian Splatting SLAM for Underwater Streaming Reconstruction
Recent monocular 3D Gaussian Splatting (3DGS) streaming reconstruction methods have achieved impressive performance by balancing reconstruction quality and efficiency. However, extending these framewo...
arXiv Computer Vision
Sep 18
SplashSplat: Reconstructing Splashing Liquids from Real-World Multi-View Videos
SplashSplat introduces a new benchmark of 20 real-world splashing liquid scenes captured with seven synchronized 4K cameras at 60 fps, providing per-view liquid and container masks and fixed evaluation splits. The method reconstructs per‑frame liquid signed distance fields (SDFs) from these masks, fuses them into a coarse velocity field, and uses Lagrangian carriers to generate differentiable local Gaussian representations for rendering. SplashSplat outperforms existing dynamic Gaussian splatting techniques on both real and synthetic data, offering more physically plausible motion, lower training cost, and enabling temporal interpolation and style transfer without re‑optimization.