Related papers: SDD-4DGS: Static-Dynamic Aware Decoupling in Gauss…
Urban scene reconstruction is critical for autonomous driving, enabling structured 3D representations for data synthesis and closed-loop testing. Supervised approaches rely on costly human annotations and lack scalability, while current…
While dynamic novel view synthesis from 2D videos has seen progress, achieving efficient reconstruction and rendering of dynamic scenes remains a challenging task. In this paper, we introduce Disentangled 4D Gaussian Splatting…
Recently, Gaussian splatting has received more and more attention in the field of static scene rendering. Due to the low computational overhead and inherent flexibility of explicit representations, plane-based explicit methods are popular…
High-dynamic scene reconstruction aims to represent static background with rigid spatial features and dynamic objects with deformed continuous spatiotemporal features. Typically, existing methods adopt unified representation model (e.g.,…
We reinterpret 4D Gaussian Splatting as a continuous-time dynamical system, where scene motion arises from integrating a learned neural dynamical field rather than applying per-frame deformations. This formulation, which we call EvoGS,…
Accurate 3D reconstruction of dynamic surgical scenes from endoscopic video is essential for robotic-assisted surgery. While recent 3D Gaussian Splatting methods have shown promise in achieving high-quality reconstructions with fast…
3D Gaussian Splatting (3DGS) leverages densely distributed Gaussian primitives for high-quality scene representation and reconstruction. While existing 3DGS methods perform well in scenes with minor view variation, large view changes from…
Recent advances in Dense Simultaneous Localization and Mapping (SLAM) have demonstrated remarkable performance in static environments. However, dense SLAM in dynamic environments remains challenging. Most methods directly remove dynamic…
Persistent dynamic scene modeling for tracking and novel-view synthesis remains challenging due to the difficulty of capturing accurate deformations while maintaining computational efficiency. We propose SCas4D, a cascaded optimization…
4D Gaussian Splatting (4DGS) has recently emerged as a promising technique for capturing complex dynamic 3D scenes with high fidelity. It utilizes a 4D Gaussian representation and a GPU-friendly rasterizer, enabling rapid rendering speeds.…
Gaussian Splatting has been considered as a novel way for view synthesis of dynamic scenes, which shows great potential in AIoT applications such as digital twins. However, recent dynamic Gaussian Splatting methods significantly degrade…
Simultaneously localizing camera poses and constructing Gaussian radiance fields in dynamic scenes establish a crucial bridge between 2D images and the 4D real world. Instead of removing dynamic objects as distractors and reconstructing…
3D Gaussian Splatting (GS) enables fast and high-quality scene reconstruction, but it lacks an object-consistent and semantically aware structure. We propose Split&Splat, a framework for panoptic scene reconstruction using 3DGS. Our…
Recent 4D dynamic scene editing methods require editing thousands of 2D images used for dynamic scene synthesis and updating the entire scene with additional training loops, resulting in several hours of processing to edit a single dynamic…
4D Gaussian Splatting (4DGS) has recently gained considerable attention as a method for reconstructing dynamic scenes. Despite achieving superior quality, 4DGS typically requires substantial storage and suffers from slow rendering speed. In…
3D Gaussian Splatting, known for enabling high-quality static scene reconstruction with fast rendering, is increasingly being applied to multi-view dynamic scene reconstruction. A common strategy involves learning a deformation field to…
We introduce Gaussian-Flow, a novel point-based approach for fast dynamic scene reconstruction and real-time rendering from both multi-view and monocular videos. In contrast to the prevalent NeRF-based approaches hampered by slow training…
High-fidelity reconstruction of dynamic scenes is an important yet challenging problem. While recent 4D Gaussian Splatting (4DGS) has demonstrated the ability to model temporal dynamics, it couples Gaussian motion and geometric attributes…
While novel view synthesis for dynamic scenes has made significant progress, capturing skeleton models of objects and re-posing them remains a challenging task. To tackle this problem, in this paper, we propose a novel approach to…
Dynamic 3D scene representation and novel view synthesis are crucial for enabling immersive experiences required by AR/VR and metaverse applications. It is a challenging task due to the complexity of unconstrained real-world scenes and…