Related papers: SemGS: Feed-Forward Semantic 3D Gaussian Splatting…
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.…
Synthesizing consistent and photorealistic 3D scenes is an open problem in computer vision. Video diffusion models generate impressive videos but cannot directly synthesize 3D representations, i.e., lack 3D consistency in the generated…
3D Gaussian Splatting-based indoor open-world free-view synthesis approaches have shown significant performance with dense input images. However, they exhibit poor performance when confronted with sparse inputs, primarily due to the sparse…
3D Gaussian Splatting offers expressive scene reconstruction, modeling a broad range of visual, geometric, and semantic information. However, efficient real-time map reconstruction with data streamed from multiple robots and devices remains…
3D scene representations have gained immense popularity in recent years. Methods that use Neural Radiance fields are versatile for traditional tasks such as novel view synthesis. In recent times, some work has emerged that aims to extend…
Scene view synthesis, which generates novel views from limited perspectives, is increasingly vital for applications like virtual reality, augmented reality, and robotics. Unlike object-based tasks, such as generating 360{\deg} views of a…
Recently, 3D Gaussian Splatting (3DGS) has shown encouraging performance for open vocabulary scene understanding tasks. However, previous methods cannot distinguish 3D instance-level information, which usually predicts a heatmap between the…
This paper presents Planar Gaussian Splatting (PGS), a novel neural rendering approach to learn the 3D geometry and parse the 3D planes of a scene, directly from multiple RGB images. The PGS leverages Gaussian primitives to model the scene…
Semantic scene understanding is crucial for robotics and computer vision applications. In autonomous driving, 3D semantic segmentation plays an important role for enabling safe navigation. Despite significant advances in the field, the…
Gaussian Splatting (GS) has recently marked a significant advancement in 3D reconstruction, delivering both rapid rendering and high-quality results. However, existing 3DGS methods pose challenges in understanding underlying 3D semantics,…
We present Generative Semantic Segmentation (GSS), a generative learning approach for semantic segmentation. Uniquely, we cast semantic segmentation as an image-conditioned mask generation problem. This is achieved by replacing the…
Semantic segmentation using deep neural networks has been widely explored to generate high-level contextual information for autonomous vehicles. To acquire a complete $180^\circ$ semantic understanding of the forward surroundings, we…
Comprehensive scene understanding is a critical enabler of robot autonomy. Semantic segmentation is one of the key scene understanding tasks which is pivotal for several robotics applications including autonomous driving, domestic service…
The primary focus of most recent works on open-vocabulary neural fields is extracting precise semantic features from the VLMs and then consolidating them efficiently into a multi-view consistent 3D neural fields representation. However,…
We present MS-Splatting -- a multi-spectral 3D Gaussian Splatting (3DGS) framework that is able to generate multi-view consistent novel views from images of multiple, independent cameras with different spectral domains. In contrast to…
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…
3D Gaussian Splatting (3D-GS) enables real-time 3D scene reconstruction but lacks robust segmentation for editing tasks such as object removal, extraction, and recoloring. Existing approaches that lift 2D segmentations to the 3D domain…
Radiance fields represented by 3D Gaussians excel at synthesizing novel views, offering both high training efficiency and fast rendering. However, with sparse input views, the lack of multi-view consistency constraints results in poorly…
In-the-wild photo collections often contain limited volumes of imagery and exhibit multiple appearances, e.g., taken at different times of day or seasons, posing significant challenges to scene reconstruction and novel view synthesis.…
Recently, 3D Gaussian Splatting and its derivatives have achieved significant breakthroughs in large-scale scene reconstruction. However, how to efficiently and stably achieve high-quality geometric fidelity remains a core challenge. To…