Related papers: ShelfGaussian: Shelf-Supervised Open-Vocabulary Ga…

While visual-language models have profoundly linked features between texts and images, the incorporation of 3D modality data, such as point clouds and 3D Gaussians, further enables pretraining for 3D-related tasks, e.g., cross-modal…

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…

3D Gaussian Splatting (3DGS) enables high-fidelity real-time rendering, a key requirement for immersive applications. However, the extension of 3DGS to dynamic scenes remains limitations on the substantial data volume of dense Gaussians and…

Simultaneous localization and mapping is essential for position tracking and scene understanding. 3D Gaussian-based map representations enable photorealistic reconstruction and real-time rendering of scenes using multiple posed cameras. We…

3D Gaussian Splatting SLAM has emerged as a widely used technique for high-fidelity mapping in spatial intelligence. However, existing methods often rely on a single representation scheme, which limits their performance in large-scale…

3D Gaussian Splatting (3DGS) enables efficient training and fast novel view synthesis in static environments. To address challenges posed by transient objects, distractor-free 3DGS methods have emerged and shown promising results when dense…

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…

We introduce the task of predicting functional 3D scene graphs for real-world indoor environments from posed RGB-D images. Unlike traditional 3D scene graphs that focus on spatial relationships of objects, functional 3D scene graphs capture…

Real objects that inhabit the physical world follow physical laws and thus behave plausibly during interaction with other physical objects. However, current methods that perform 3D reconstructions of real-world scenes from multi-view 2D…

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…

Recently, 3D Gaussian splatting (3DGS) has gained considerable attentions in the field of novel view synthesis due to its fast performance while yielding the excellent image quality. However, 3DGS in sparse-view settings (e.g., three-view…

Visualization of large-scale time-dependent simulation data is crucial for domain scientists to analyze complex phenomena, but it demands significant I/O bandwidth, storage, and computational resources. To enable effective visualization on…

Recent advancements in multi-modal 3D pre-training methods have shown promising efficacy in learning joint representations of text, images, and point clouds. However, adopting point clouds as 3D representation fails to fully capture the…

Zero-shot neural scene segmentation, which reconstructs 3D neural segmentation field without manual annotations, serves as an effective way for scene understanding. However, existing models, especially the efficient 3D Gaussian-based…

Forecasting future scenarios in dynamic environments is essential for intelligent decision-making and navigation, a challenge yet to be fully realized in computer vision and robotics. Traditional approaches like video prediction and…

Open-vocabulary 3D scene understanding presents a significant challenge in the field. Recent works have sought to transfer knowledge embedded in vision-language models from 2D to 3D domains. However, these approaches often require prior…

3D occupancy prediction enables the robots to obtain spatial fine-grained geometry and semantics of the surrounding scene, and has become an essential task for embodied perception. Existing methods based on 3D Gaussians instead of dense…

This paper presents a pose-free, feed-forward 3D Gaussian Splatting (3DGS) framework designed to handle unfavorable input views. A common rendering setup for training feed-forward approaches places a 3D object at the world origin and…

Jointly estimating camera poses and mapping scenes from RGBD images is a fundamental task in simultaneous localization and mapping (SLAM). State-of-the-art methods employ 3D Gaussians to represent a scene, and render these Gaussians through…

Human vision is capable of transforming two-dimensional observations into an egocentric three-dimensional scene understanding, which underpins the ability to translate complex scenes and exhibit adaptive behaviors. This capability, however,…