Related papers: {\Psi}-Map: Panoptic Surface Integrated Mapping En…

Complete reconstruction of surgical scenes is crucial for robot-assisted surgery (RAS). Deep depth estimation is promising but existing works struggle with depth discontinuities, resulting in noisy predictions at object boundaries and do…

Recent advances in 3D Gaussian Splatting have shown remarkable potential for novel view synthesis. However, most existing large-scale scene reconstruction methods rely on the divide-and-conquer paradigm, which often leads to the loss of…

Real-time reconstruction of deformable surgical scenes is vital for advancing robotic surgery, improving surgeon guidance, and enabling automation. Recent methods achieve dense reconstructions from da Vinci robotic surgery videos, with…

Recently, Gaussian Splatting (GS) has received a lot of attention in surface reconstruction. However, while 3D objects can be of complex and diverse shapes in the real world, existing GS-based methods only limitedly use a single type of…

In robot-assisted minimally invasive surgery, high-fidelity dynamic endoscopic scene reconstruction and simulation are crucial to enhancing downstream tasks and advancing surgical outcomes. However, existing methods primarily focus on…

In this paper, we rethink the problem of scene reconstruction from an embodied agent's perspective: While the classic view focuses on the reconstruction accuracy, our new perspective emphasizes the underlying functions and constraints such…

We present HI-SLAM2, a geometry-aware Gaussian SLAM system that achieves fast and accurate monocular scene reconstruction using only RGB input. Existing Neural SLAM or 3DGS-based SLAM methods often trade off between rendering quality and…

Exploiting internal spatial geometric constraints of sparse LiDARs is beneficial to depth completion, however, has been not explored well. This paper proposes an efficient method to learn geometry-aware embedding, which encodes the local…

Recent advancements in multi-view 3D reconstruction and novel-view synthesis, particularly through Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), have greatly enhanced the fidelity and efficiency of 3D content creation.…

In this study, we address the challenge of constructing continuous three-dimensional (3D) models that accurately represent uncertain surfaces, derived from noisy and incomplete LiDAR scanning data. Building upon our prior work, which…

3D Gaussian Splatting (3DGS) enables high-quality real-time 3D rendering but faces challenges in efficiently scaling to ultra-dense scenes and high-resolution due to computational bottlenecks that limit its use in latency-sensitive…

This paper presents the first photo-realistic LiDAR-Inertial-Camera Gaussian Splatting SLAM system that simultaneously addresses visual quality, geometric accuracy, and real-time performance. The proposed method performs robust and accurate…

3D Gaussian Splatting (3DGS) has recently unlocked real-time, high-fidelity novel view synthesis by representing scenes using explicit 3D primitives. However, traditional methods often require millions of Gaussians to capture complex…

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…

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…

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…

Robots benefit from high-fidelity reconstructions of their environment, which should be geometrically accurate and photorealistic to support downstream tasks. While this can be achieved by building distance fields from range sensors and…

Accurate and affordable indoor 3D reconstruction is critical for effective robot navigation and interaction. Traditional LiDAR-based mapping provides high precision but is costly, heavy, and power-intensive, with limited ability for novel…

Understanding the geometric and semantic structure of environments is essential for embodied navigation and reasoning. Existing semantic mapping methods trade off between explicit geometry and multi-scale semantics, and lack a native…

Reliable multimodal sensor fusion algorithms require accurate spatiotemporal calibration. Recently, targetless calibration techniques based on implicit neural representations have proven to provide precise and robust results. Nevertheless,…