Related papers: DynamicGSG: Dynamic 3D Gaussian Scene Graphs for E…
Recent advancements in dynamic 3D scene reconstruction have shown promising results, enabling high-fidelity 3D novel view synthesis with improved temporal consistency. Among these, 4D Gaussian Splatting (4DGS) has emerged as an appealing…
Recent advances in novel-view synthesis can create the photo-realistic visualization of real-world environments from conventional camera captures. However, the everyday environment experiences frequent scene changes, which require dense…
Modern 3D engines and graphics pipelines require mesh as a memory-efficient representation, which allows efficient rendering, geometry processing, texture editing, and many other downstream operations. However, it is still highly difficult…
High-level autonomous operations depend on a robot's ability to construct a sufficiently expressive model of its environment. Traditional three-dimensional (3D) scene representations, such as point clouds and occupancy grids, provide…
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…
Real-time rendering of dynamic scenes with view-dependent effects remains a fundamental challenge in computer graphics. While recent advances in Gaussian Splatting have shown promising results separately handling dynamic scenes (4DGS) and…
Maintaining an up-to-date map that accurately reflects recent changes in the environment is crucial, especially for robots that repeatedly traverse the same space. Failing to promptly update the changed regions can degrade map quality,…
Reconstructing dynamic scenes with large-scale and complex motions remains a significant challenge. Recent techniques like Neural Radiance Fields and 3D Gaussian Splatting (3DGS) have shown promise but still struggle with scenes involving…
Performing language-conditioned robotic manipulation tasks in unstructured environments is highly demanded for general intelligent robots. Conventional robotic manipulation methods usually learn semantic representation of the observation…
This paper investigates an open research challenge of reconstructing high-quality, large 3D open scenes from images. It is observed existing methods have various limitations, such as requiring precise camera poses for input and dense…
3D Gaussian Splatting (3DGS) has shown promising performance in novel view synthesis. Previous methods adapt it to obtaining surfaces of either individual 3D objects or within limited scenes. In this paper, we make the first attempt to…
Rendering novel view images in dynamic scenes is a crucial yet challenging task. Current methods mainly utilize NeRF-based methods to represent the static scene and an additional time-variant MLP to model scene deformations, resulting in…
3D Gaussian Splatting (3DGS) has shown remarkable success in synthesizing novel views given multiple views of a static scene. Yet, 3DGS faces challenges when applied to dynamic scenes because 3D Gaussian parameters need to be updated per…
Reconstructing large-scale dynamic driving scenes remains challenging due to the coexistence of static environments with extreme depth variation and diverse dynamic actors exhibiting complex motions. Existing Gaussian Splatting based…
We present DrivingGaussian, an efficient and effective framework for surrounding dynamic autonomous driving scenes. For complex scenes with moving objects, we first sequentially and progressively model the static background of the entire…
Achieving unified 3D perception and reasoning across tasks such as segmentation, retrieval, and relation understanding remains challenging, as existing methods are either object-centric or rely on costly training for inter-object reasoning.…
Semantic understanding of 3D scenes is essential for robots to operate effectively and safely in complex environments. Existing methods for semantic scene reconstruction and semantic-aware novel view synthesis often rely on dense multi-view…
Representing and rendering dynamic scenes has been an important but challenging task. Especially, to accurately model complex motions, high efficiency is usually hard to guarantee. To achieve real-time dynamic scene rendering while also…
The advancement of real-time 3D scene reconstruction and novel view synthesis has been significantly propelled by 3D Gaussian Splatting (3DGS). However, effectively training large-scale 3DGS and rendering it in real-time across various…
Current 4D Gaussian frameworks for dynamic scene reconstruction deliver impressive visual fidelity and rendering speed, however, the inherent trade-off between storage costs and the ability to characterize complex physical motions…