Related papers: GaussianFormer-2: Probabilistic Gaussian Superposi…

Despite the substantial progress of novel view synthesis, existing methods, either based on the Neural Radiance Fields (NeRF) or more recently 3D Gaussian Splatting (3DGS), suffer significant degradation when the input becomes sparse.…

Open-vocabulary scene understanding using 3D Gaussian (3DGS) representations has garnered considerable attention. However, existing methods mostly lift knowledge from large 2D vision models into 3DGS on a scene-by-scene basis, restricting…

We describe an approach to predict open-vocabulary 3D semantic voxel occupancy map from input 2D images with the objective of enabling 3D grounding, segmentation and retrieval of free-form language queries. This is a challenging problem…

3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis. However, existing methods struggle to adaptively optimize the distribution of Gaussian primitives based on scene characteristics, making it…

Autonomous vehicles commonly rely on highly detailed birds-eye-view maps of their environment, which capture both static elements of the scene such as road layout as well as dynamic elements such as other cars and pedestrians. Generating…

3D semantic occupancy prediction, which seeks to provide accurate and comprehensive representations of environment scenes, is important to autonomous driving systems. For autonomous cars equipped with multi-camera and LiDAR, it is critical…

Gaussian splatting, renowned for its exceptional rendering quality and efficiency, has emerged as a prominent technique in 3D scene representation. However, the substantial data volume of Gaussian splatting impedes its practical utility in…

While Gaussian Splatting-based Feature Fields (GSFFs) have shown promise for visual localization, this paper highlights that photometrically optimized GSFFs are inherently ill-suited for 2D-3D matching. The volumetric extent of each…

We have introduced SegSplat, a novel framework designed to bridge the gap between rapid, feed-forward 3D reconstruction and rich, open-vocabulary semantic understanding. By constructing a compact semantic memory bank from multi-view 2D…

Semantic scene completion (SSC) aims to predict the semantic occupancy of each voxel in the entire 3D scene from limited observations, which is an emerging and critical task for autonomous driving. Recently, many studies have turned to…

Holistic 3D scene understanding, which jointly models geometry, appearance, and semantics, is crucial for applications like augmented reality and robotic interaction. Existing feed-forward 3D scene understanding methods (e.g., LSM) are…

3D Gaussian Splatting (3DGS) has garnered significant attention due to its superior scene representation fidelity and real-time rendering performance, especially for dynamic 3D scene reconstruction (\textit{i.e.}, 4D reconstruction).…

3D open-vocabulary scene understanding, crucial for advancing augmented reality and robotic applications, involves interpreting and locating specific regions within a 3D space as directed by natural language instructions. To this end, we…

Relying on in-domain annotations and precise sensor-rig priors, existing 3D occupancy prediction methods are limited in both scalability and out-of-domain generalization. While recent visual geometry foundation models exhibit strong…

Vision-centric occupancy networks, which represent the surrounding environment with uniform voxels with semantics, have become a new trend for safe driving of camera-only autonomous driving perception systems, as they are able to detect…

Computing the posterior distribution of a probabilistic program is a hard task for which no one-fit-for-all solution exists. We propose Gaussian Semantics, which approximates the exact probabilistic semantics of a bounded program by means…

3D Gaussian Splatting (3DGS) provides an explicit and efficient scene representation, but its primitives lack inherent object-level identity, hindering downstream tasks such as open-vocabulary scene understanding. Existing methods typically…

This paper begins with a description of methods for estimating image probability density functions that reflects the observation that such data is usually constrained to lie in restricted regions of the high-dimensional image space-not…

3D Gaussian Splatting (3DGS) has emerged as a powerful explicit representation enabling real-time, high-fidelity 3D reconstruction and novel view synthesis. However, its practical use is hindered by the massive memory and computational…

Visual-based 3D semantic occupancy perception is a key technology for robotics, including autonomous vehicles, offering an enhanced understanding of the environment by 3D. This approach, however, typically requires more computational…