Related papers: FMLGS: Fast Multilevel Language Embedded Gaussians…
Bridging the gap between complex human instructions and precise 3D object grounding remains a significant challenge in vision and robotics. Existing 3D segmentation methods often struggle to interpret ambiguous, reasoning-based…
Understanding semantics and dynamics has been crucial for embodied agents in various tasks. Both tasks have much more data redundancy than the static scene understanding task. We formulate the view selection problem as an active learning…
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…
Object navigation is a core capability of embodied intelligence, enabling an agent to locate target objects in unknown environments. Recent advances in vision-language models (VLMs) have facilitated zero-shot object navigation (ZSON).…
Humans naturally interact with their 3D surroundings using language, and modeling 3D language fields for scene understanding and interaction has gained growing interest. This paper introduces ChatSplat, a system that constructs a 3D…
Open-vocabulary 3D visual grounding and reasoning aim to localize objects in a scene based on implicit language descriptions, even when they are occluded. This ability is crucial for tasks such as vision-language navigation and autonomous…
Recent advancements in 3D generation models have opened new possibilities for simulating dynamic 3D object movements and customizing behaviors, yet creating this content remains challenging. Current methods often require manual assignment…
3D affordance reasoning, the task of associating human instructions with the functional regions of 3D objects, is a critical capability for embodied agents. Current methods based on 3D Gaussian Splatting (3DGS) are fundamentally limited to…
Extending 3D Gaussian Splatting (3DGS) to 4D physical simulation remains challenging. Based on the Material Point Method (MPM), existing methods either rely on manual parameter tuning or distill dynamics from video diffusion models,…
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…
Open-vocabulary querying in 3D space is crucial for enabling more intelligent perception in applications such as robotics, autonomous systems, and augmented reality. However, most existing methods rely on 2D pixel-level parsing, leading to…
In this paper, we propose a RGB-D SLAM system that reconstructs a language-aligned dense feature field while sustaining low-latency tracking and mapping. First, we introduce a Top-K Rendering pipeline, a high-throughput and…
We propose a novel cross-spectral rendering framework based on 3D Gaussian Splatting (3DGS) that generates realistic and semantically meaningful splats from registered multi-view spectrum and segmentation maps. This extension enhances the…
Modeling 3D language fields with Gaussian Splatting for open-ended language queries has recently garnered increasing attention. However, recent 3DGS-based models leverage view-dependent 2D foundation models to refine 3D semantics but lack a…
Open-vocabulary panoptic reconstruction is crucial for advanced robotics and simulation. However, existing 3D reconstruction methods, such as NeRF or Gaussian Splatting variants, often struggle to achieve the real-time inference frequency…
3D Gaussian Splatting (3DGS) has emerged as a prominent 3D representation for high-fidelity and real-time rendering. Prior work has coupled physics simulation with Gaussians, but predominantly targets soft, deformable materials, leaving…
3D Gaussian Splatting has advanced radiance field reconstruction, enabling high-quality view synthesis and fast rendering in 3D modeling. While adversarial attacks on object detection models are well-studied for 2D images, their impact on…
Recently, the multi-modal fusion of RGB, depth, and semantics has shown great potential in dense Simultaneous Localization and Mapping (SLAM). However, a prerequisite for generating consistent semantic maps is the availability of dense,…
Establishing dense correspondence across 3D shapes is crucial for fundamental downstream tasks, including texture transfer, shape interpolation, and robotic manipulation. However, learning these mappings without manual supervision remains a…
We address the challenge of task-oriented navigation in unstructured and unknown environments, where robots must incrementally build and reason on rich, metric-semantic maps in real time. Since tasks may require clarification or…