Related papers: UniGS: Unified Language-Image-3D Pretraining with …
3D Shape represented as point cloud has achieve advancements in multimodal pre-training to align image and language descriptions, which is curial to object identification, classification, and retrieval. However, the discrete representations…
The scale diversity of point cloud data presents significant challenges in developing unified representation learning techniques for 3D vision. Currently, there are few unified 3D models, and no existing pre-training method is equally…
Recent works in 3D multimodal learning have made remarkable progress. However, typically 3D multimodal models are only capable of handling point clouds. Compared to the emerging 3D representation technique, 3D Gaussian Splatting (3DGS), the…
In this paper, we propose UniGS, a unified map representation and differentiable framework for high-fidelity multimodal 3D reconstruction based on 3D Gaussian Splatting. Our framework integrates a CUDA-accelerated rasterization pipeline…
The significance of informative and robust point representations has been widely acknowledged for 3D scene understanding. Despite existing self-supervised pre-training counterparts demonstrating promising performance, the model collapse and…
In this work, we introduce UniGS, a novel 3D Gaussian reconstruction and novel view synthesis model that predicts a high-fidelity representation of 3D Gaussians from arbitrary number of posed sparse-view images. Previous methods often…
Self-supervised learning of point cloud aims to leverage unlabeled 3D data to learn meaningful representations without reliance on manual annotations. However, current approaches face challenges such as limited data diversity and inadequate…
Joint rendering and deformation of mesh and 3D Gaussian Splatting (3DGS) have significant value as both representa tions offer complementary advantages for graphics applica tions. However, due to differences in representation and ren dering…
Recent advancements in 3D reconstruction coupled with neural rendering techniques have greatly improved the creation of photo-realistic 3D scenes, influencing both academic research and industry applications. The technique of 3D Gaussian…
Unsupervised point cloud segmentation is critical for embodied artificial intelligence and autonomous driving, as it mitigates the prohibitive cost of dense point-level annotations required by fully supervised methods. While integrating 2D…
Semantic-aware 3D reconstruction from sparse, unposed images remains challenging for feed-forward 3D Gaussian Splatting (3DGS). Existing methods often predict an over-complete set of Gaussian primitives under sparse-view supervision,…
Open-vocabulary 3D scene understanding is crucial for applications requiring natural language-driven spatial interpretation, such as robotics and augmented reality. While 3D Gaussian Splatting (3DGS) offers a powerful representation for…
Recent advancements in 3D scene understanding have made significant strides in enabling interaction with scenes using open-vocabulary queries, particularly for VR/AR and robotic applications. Nevertheless, existing methods are hindered by…
3D Gaussian Splatting (3DGS) has emerged as a powerful and efficient 3D representation for novel view synthesis. This paper extends 3DGS capabilities to inpainting, where masked objects in a scene are replaced with new contents that blend…
We propose a feed-forward Gaussian Splatting model that unifies 3D scene and semantic field reconstruction. Combining 3D scenes with semantic fields facilitates the perception and understanding of the surrounding environment. However, key…
3D Gaussian Splatting (3DGS) has emerged as a novel explicit representation for 3D scenes, offering both high-fidelity reconstruction and efficient rendering. However, 3DGS lacks 3D segmentation ability, which limits its applicability in…
Pre-training on large-scale unlabeled datasets contribute to the model achieving powerful performance on 3D vision tasks, especially when annotations are limited. However, existing rendering-based self-supervised frameworks are…
Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction without the need for per-scene optimization. However, existing feedforward approaches typically…
Precisely perceiving the geometric and semantic properties of real-world 3D objects is crucial for the continued evolution of augmented reality and robotic applications. To this end, we present Foundation Model Embedded Gaussian Splatting…
A well-designed vectorized representation is crucial for the learning systems natively based on 3D Gaussian Splatting. While 3DGS enables efficient and explicit 3D reconstruction, its parameter-based representation remains hard to learn as…