Related papers: FLEG: Feed-Forward Language Embedded Gaussian Spla…
We present LangFlash, a feed-forward framework for 3D Language Gaussian Splatting that reconstructs 3D scenes parameterized by Gaussian primitives enriched with language-aligned semantic features from sparse unposed multi-view images.…
Language-augmented scene representations hold great promise for large-scale robotics applications such as search-and-rescue, smart cities, and mining. Many of these scenarios are time-sensitive, requiring rapid scene encoding while also…
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…
Recently, several studies have combined Gaussian Splatting to obtain scene representations with language embeddings for open-vocabulary 3D scene understanding. While these methods perform well, they essentially require very dense multi-view…
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…
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…
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…
3D Gaussian Splatting has recently gained traction for its efficient training and real-time rendering. While its vanilla representation is mainly designed for view synthesis, recent works extended it to scene understanding with language…
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…
Recent advances in feed-forward 3D Gaussian Splatting have led to rapid improvements in efficient scene reconstruction from sparse views. However, most existing approaches construct Gaussian primitives directly aligned with the pixels in…
Building semantic 3D maps is valuable for searching for objects of interest in offices, warehouses, stores, and homes. We present a mapping system that incrementally builds a Language-Embedded Gaussian Splat (LEGS): a detailed 3D scene…
We introduce FLAG-4D, a novel framework for generating novel views of dynamic scenes by reconstructing how 3D Gaussian primitives evolve through space and time. Existing methods typically rely on a single Multilayer Perceptron (MLP) to…
Modern Gaussian Splatting methods have proven highly effective for real-time photorealistic rendering of 3D scenes. However, integrating semantic information into this representation remains a significant challenge, especially in…
Capturing relightable 3D assets from real-world objects is a widely researched problem. Several per-scene optimization-based methods, based on 3D Gaussian splatting (3DGS), support relighting; however, they usually require dense input…
Feed-forward 3D Gaussian Splatting (3DGS) has emerged as a highly effective solution for novel view synthesis. Existing methods predominantly rely on a \emph{pixel-aligned} Gaussian prediction paradigm, where each 2D pixel is mapped to a 3D…
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.…
We present LSeg, a novel model for language-driven semantic image segmentation. LSeg uses a text encoder to compute embeddings of descriptive input labels (e.g., "grass" or "building") together with a transformer-based image encoder that…
Feed-forward 3D Gaussian Splatting methods enable single-pass reconstruction and real-time rendering. However, they typically adopt rigid pixel-to-Gaussian or voxel-to-Gaussian pipelines that uniformly allocate Gaussians, leading to…
Recent advances in 3D Gaussian Splatting (3DGS) have enabled Simultaneous Localization and Mapping (SLAM) systems to build photorealistic maps. However, these maps lack the open-vocabulary semantic understanding required for advanced…
Embedding a language field in a 3D representation enables richer semantic understanding of spatial environments by linking geometry with descriptive meaning. This allows for a more intuitive human-computer interaction, enabling querying or…