3D Gaussian Splatting (3DGS) has become the de facto method of 3D representation in
many vision tasks. This calls for the 3D understanding directly in this representation space …

Large-scale 3D reconstruction is critical in the field of robotics, and the potential of 3D
Gaussian Splatting (3DGS) for achieving accurate object-level reconstruction has been …

3D Gaussian Splatting has recently shown promising results as an alternative scene
representation in SLAM systems to neural implicit representations. However, current …

Previous surface reconstruction methods either suffer from low geometric accuracy or
lengthy training times when dealing with real-world complex dynamic scenes involving multi …

While neural 3D reconstruction has advanced substantially, it typically requires densely
captured multi-view data with carefully initialized poses (eg, using COLMAP). However, this …

We present MegaSurf, a Neural Surface Reconstruction (NSR) framework to reconstruct 3D
models of large scenes from aerial images. Many methods utilize geometry cues to …

Recently, 3D Gaussian Splatting (3DGS) has achieved significant performance on indoor
surface reconstruction and open-vocabulary segmentation. This paper presents GLS, a …

Robots require high-fidelity reconstructions of their environment for effective operation. Such
scene representations should be both, geometrically accurate and photorealistic to support …

Neural Radiance Fields (NeRF) have advanced 3D reconstruction by learning implicit
representations of scenes from multi-view images, yet their effectiveness is limited in …