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 geometry accuracy, our research demonstrates that both can be achieved simultaneously with RGB input alone. The key idea of our approach is to enhance the ability for geometry estimation by combining easy-to-obtain monocular priors with learning-based dense SLAM, and then using 3D Gaussian splatting as our core map representation to efficiently model the scene. Upon loop closure, our method ensures on-the-fly global consistency through efficient pose graph bundle adjustment and instant map updates by explicitly deforming the 3D Gaussian units based on anchored keyframe updates. Furthermore, we introduce a grid-based scale alignment strategy to maintain improved scale consistency in prior depths for finer depth details. Through extensive experiments on Replica, ScanNet, and ScanNet++, we demonstrate significant improvements over existing Neural SLAM methods and even surpass RGB-D-based methods in both reconstruction and rendering quality.

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 geometry accuracy, our research demonstrates that both can be achieved simultaneously with RGB input alone. The key idea of our approach is to enhance the ability for geometry estimation by combining easy-to-obtain monocular priors with learning-based dense SLAM, and then using 3D Gaussian splatting as our core map representation to efficiently model the scene. Upon loop closure, our method ensures on-the-fly global consistency through efficient pose graph bundle adjustment and instant map updates by explicitly deforming the 3D Gaussian units based on anchored keyframe updates. Furthermore, we introduce a grid-based scale alignment strategy to maintain improved scale consistency in prior depths for finer depth details. Through extensive experiments on Replica, ScanNet, Waymo Open, ETH3D SLAM and ScanNet++ datasets, we demonstrate significant improvements over existing Neural SLAM methods and even surpass RGB-D-based methods in both reconstruction and rendering quality.

We propose a new method for fine registering multiple point clouds simultaneously. The approach is characterized by being dense, therefore point clouds are not reduced to pre-selected features in advance. Furthermore, the approach is robust against small overlaps and dynamic objects, since no direct correspondences are assumed between point clouds. Instead, all points are merged into a global point cloud, whose scattering is then iteratively reduced. This is achieved by dividing the global point cloud into uniform grid cells whose contents are subsequently modeled by normal distributions. We show that the proposed approach can be used in a sliding window continuous trajectory optimization combined with IMU measurements to obtain a highly accurate and robust LiDAR inertial odometry estimation. Furthermore, we show that the proposed approach is also suitable for large scale keyframe optimization to increase accuracy. We provide the source code and some experimental data on https://github.com/davidskdds/DMSA_LiDAR_SLAM.git.

While originally developed for novel view synthesis, Neural Radiance Fields (NeRFs) are currently emerging as an alternative to multi-view stereo (MVS). Promising results have been gained especially for texture-less, transparent, and reflecting surfaces, while such scenarios remain challenging for traditional MVS-based approaches. However, most investigations focus on close-range scenarios, with studies for airborne scenarios still missing. There, NeRFs face potential difficulties at areas of low image redundancy and weak data evidence, as i.e. in street canyons, facades or building shadows. Furthermore, training such networks is computationally expensive. We investigate the applicability of NeRFs for aerial image blocks representing different characteristics like nadir-only, oblique and high-resolution imagery. Furthermore, we demonstrate the benefit of integrating depth priors from tie-point measures, which are provided during presupposed Bundle Block Adjustment. Our work is based on the state-of-the-art framework VolSDF, which models 3D scenes by signed distance functions (SDFs). For evaluation, the NeRF-based reconstructions are compared to results of a publicly available benchmark dataset for airborne images.

In this paper, we present BAMF-SLAM, a novel multi-fisheye visual-inertial SLAM system that utilizes Bundle Adjustment (BA) and recurrent field transforms (RFT) to achieve accurate and robust state estimation in challenging scenarios. First, our system directly operates on raw fisheye images, enabling us to fully exploit the wide Field-of-View (FoV) of fisheye cameras. Second, to overcome the low-texture challenge, we explore the tightly-coupled integration of multi-camera inputs and complementary inertial measurements via a unified factor graph and jointly optimize the poses and dense depth maps. Third, for global consistency, the wide FoV of the fisheye camera allows the system to find more potential loop closures, and powered by the broad convergence basin of RFT, our system can perform very wide baseline loop closing with little overlap. Furthermore, we introduce a semi-pose-graph BA method to avoid the expensive full global BA. By combining relative pose factors with loop closure factors, the global states can be adjusted efficiently with modest memory footprint while maintaining high accuracy. Evaluations on TUM-VI, Hilti-Oxford and Newer College datasets show the superior performance of the proposed system over prior works. In the Hilti SLAM Challenge 2022, our VIO version achieves second place. In a subsequent submission, our complete system, including the global BA backend, outperforms the winning approach.

We present an algorithm for extracting Level of Detail 2 (LOD2) building models from video streams captured by Unmaned Aerial Vehicles (UAVs). Typically, such imagery is of limited radiometric quality but the surface is captured with large redundancy. The first contribution of this paper is a novel algorithm exploiting this redundancy for precise depth computation. This is realized by fusing consistent depth estimations across single stereo models and generating a 2.5D elevation map from the resulting point clouds. Disparity maps are derived by a coarse-to-fine Semi-Global-Matching (SGM) method performing well on noisy imagery. The second contribution concerns a challenging step of the context-based urban terrain modeling: Dominant planes extraction for building reconstruction. Because of noisy data and complicated roof structures, both dominant plane parameters and initial values for support sets of planes are obtained by the J-Linkage algorithm. An improved point-to-plane labeling is presented to encourage the assignment of proximate points to the same plane. This is accomplished by non-local, Markov Random Field (MRF) - based optimization and segmentation of color information. The potential and the limitations of the proposed methods are shown using an UAV video sequence of limited radiometric quality.