LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling
read the original abstract
Due to the complex and highly dynamic motions in the real world, synthesizing dynamic videos from multi-view inputs for arbitrary viewpoints is challenging. Previous works based on neural radiance field or 3D Gaussian splatting are limited to modeling fine-scale motion, greatly restricting their application. In this paper, we introduce LocalDyGS, which consists of two parts to adapt our method to both large-scale and fine-scale motion scenes: 1) We decompose a complex dynamic scene into streamlined local spaces defined by seeds, enabling global modeling by capturing motion within each local space. 2) We decouple static and dynamic features for local space motion modeling. A static feature shared across time steps captures static information, while a dynamic residual field provides time-specific features. These are combined and decoded to generate Temporal Gaussians, modeling motion within each local space. As a result, we propose a novel dynamic scene reconstruction framework to model highly dynamic real-world scenes more realistically. Our method not only demonstrates competitive performance on various fine-scale datasets compared to state-of-the-art (SOTA) methods, but also represents the first attempt to model larger and more complex highly dynamic scenes. Project page: https://wujh2001.github.io/LocalDyGS/.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
DLGStream: Dynamic Language-embedded Guassian Splatting for Open-vocabulary Enabled Free-viewpoint Video Streaming
DLGStream introduces dual-opacity dynamic language Gaussians and an interpolation deformation field to enable language-embedded FVV streaming at 43 KB per frame with improved open-vocabulary segmentation and reconstru...
-
ClipGStream: Clip-Stream Gaussian Splatting for Any Length and Any Motion Multi-View Dynamic Scene Reconstruction
ClipGStream enables scalable flicker-free reconstruction of long dynamic multi-view videos by performing stream optimization at the clip level with clip-independent spatio-temporal fields, residual anchor compensation...
-
LiveStre4m: Feed-Forward Live Streaming of Novel Views from Unposed Multi-View Video
LiveStre4m delivers real-time novel-view video streaming from unposed multi-view inputs via a multi-view vision transformer, diffusion-transformer interpolation, and a learned camera pose predictor.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.