Related papers: GaussianOcc: Fully Self-supervised and Efficient 3…
The emergence of 3D Gaussian Splatting (3DGS) has greatly accelerated the rendering speed of novel view synthesis. Unlike neural implicit representations like Neural Radiance Fields (NeRF) that represent a 3D scene with position and…
3D occupancy becomes a promising perception representation for autonomous driving to model the surrounding environment at a fine-grained scale. However, it remains challenging to efficiently aggregate 3D occupancy over time across multiple…
3D scene reconstruction is a foundational problem in computer vision. Despite recent advancements in Neural Implicit Representations (NIR), existing methods often lack editability and compositional flexibility, limiting their use in…
Monocular 3D occupancy prediction, aiming to predict the occupancy and semantics within interesting regions of 3D scenes from only 2D images, has garnered increasing attention recently for its vital role in 3D scene understanding.…
Accurate and realistic 3D scene reconstruction enables the lifelike creation of autonomous driving simulation environments. With advancements in 3D Gaussian Splatting (3DGS), previous studies have applied it to reconstruct complex dynamic…
We present GSLoc: a new visual localization method that performs dense camera alignment using 3D Gaussian Splatting as a map representation of the scene. GSLoc backpropagates pose gradients over the rendering pipeline to align the rendered…
Rendering dynamic 3D human from monocular videos is crucial for various applications such as virtual reality and digital entertainment. Most methods assume the people is in an unobstructed scene, while various objects may cause the…
3D Gaussian Splatting (3D-GS) has recently attracted great attention with real-time and photo-realistic renderings. This technique typically takes perspective images as input and optimizes a set of 3D elliptical Gaussians by splatting them…
3D semantic occupancy prediction has emerged as a critical perception task for autonomous driving due to its ability to offer voxel-level semantic and geometric understanding of the environment. However, such a refined representation for…
3D Gaussian Splatting (3DGS) achieves high-fidelity rendering with fast real-time performance, but existing methods rely on offline training after full Structure-from-Motion (SfM) processing. In contrast, this work introduces Gaussian…
Open-vocabulary 3D occupancy is vital for embodied agents, which need to understand complex indoor environments where semantic categories are abundant and evolve beyond fixed taxonomies. While recent work has explored open-vocabulary…
TL;DR: Gaussian Splatting is a widely adopted approach for 3D scene representation, offering efficient, high-quality reconstruction and rendering. A key reason for its success is the simplicity of representing scenes with sets of Gaussians,…
Recent works on 3D scene understanding leverage 2D masks from visual foundation models (VFMs) to supervise radiance fields, enabling instance-level 3D segmentation. However, the supervision signals from foundation models are not…
This paper presents a novel system designed for 3D mapping and visual relocalization using 3D Gaussian Splatting. Our proposed method uses LiDAR and camera data to create accurate and visually plausible representations of the environment.…
3D semantic occupancy prediction is essential for achieving safe, reliable autonomous driving and robotic navigation. Compared to camera-only perception systems, multi-modal pipelines, especially LiDAR-camera fusion methods, can produce…
We introduce OceanSplat, a novel 3D Gaussian Splatting-based approach for high-fidelity underwater scene reconstruction. To overcome multi-view inconsistencies caused by scattering media, we design a trinocular setup for each camera pose by…
We introduce GSVisLoc, a visual localization method designed for 3D Gaussian Splatting (3DGS) scene representations. Given a 3DGS model of a scene and a query image, our goal is to estimate the camera's position and orientation. We…
Differentiable rendering techniques have recently shown promising results for free-viewpoint video synthesis of characters. However, such methods, either Gaussian Splatting or neural implicit rendering, typically necessitate per-subject…
Reconstructing and rendering 3D objects from highly sparse views is of critical importance for promoting applications of 3D vision techniques and improving user experience. However, images from sparse views only contain very limited 3D…
Learning 3D scene geometry and semantics from images is a core challenge in computer vision and a key capability for autonomous driving. Since large-scale 3D annotation is prohibitively expensive, recent work explores self-supervised…