Visual localization methods often present a trade-off between the high efficiency of specialized approaches, such as scene coordinate regression, and the need for rich, versatile scene representations for broader robotics tasks. To bridge this gap, we explore the use of 3D Gaussian Splatting (3DGS), which enables a unified, photorealistic encoding of 3D geometry and appearance. We propose GSplatLoc, a self-contained framework that tightly integrates structure-based keypoint matching with rendering-based pose refinement. Our two-stage procedure first distills robust descriptors from the lightweight XFeat extractor into the 3DGS model, enabling coarse pose estimation via 2D-3D correspondences without external dependencies. In the second stage, the initial pose is refined by minimizing a photometric warp loss, which leverages the fast, differentiable rendering of 3DGS. Benchmarking on widely used indoor and outdoor datasets demonstrates state-of-the-art performance among neural rendering-based localization methods and highlights the framework’s robustness in challenging dynamic scenes. Project page: https://gsplatloc.github.io

We present a new multi-sensor dataset for multi-view 3D surface reconstruction. It includes registered RGB and depth data from sensors of different resolutions and modalities: smartphones, Intel RealSense, Microsoft Kinect, industrial cameras, and structured-light scanner. The scenes are selected to emphasize a diverse set of material properties challenging for existing algorithms. We provide around 1.4 million images of 107 different scenes acquired from 100 viewing directions under 14 lighting conditions. We expect our dataset will be useful for evaluation and training of 3D reconstruction algorithms and for related tasks. The dataset is available at skol tech3d. appliedai. tech.

We present a new system$(NPBG++)$for the novel view synthesis (NVS) task that achieves high rendering realism with low scene fitting time. Our method efficiently lever-ages the multiview observations and the point cloud of a static scene to predict a neural descriptor for each point, improving upon the pipeline of Neural Point-Based Graph-ics [1] in several important ways. By predicting the descrip-tors with a single pass through the source images, we lift the requirement of per-scene optimization while also making the neural descriptors view-dependent and more suit-able for scenes with strong non-Lambertian effects. In our comparisons, the proposed system outperforms previous NVS approaches in terms of fitting and rendering runtimes while producing images of similar quality. Project page: https://rakhimovv.github.io/npbgpp/.

We propose Deep Estimators of Features (DEFs), a learning-based framework for predicting sharp geometric features in sampled 3D shapes. Differently from existing data-driven methods, which reduce this problem to feature classification, we propose to regress a scalar field representing the distance from point samples to the closest feature line on local patches. Our approach is the first that scales to massive point clouds by fusing distance-to-feature estimates obtained on individual patches. We extensively evaluate our approach against related state-of-the-art methods on newly proposed synthetic and real-world 3D CAD model benchmarks. Our approach not only outperforms these (with improvements in Recall and False Positives Rates), but generalizes to real-world scans after training our model on synthetic data and fine-tuning it on a small dataset of scanned data. We demonstrate a downstream application, where we reconstruct an explicit representation of straight and curved sharp feature lines from range scan data. We make code, pre-trained models, and our training and evaluation datasets available at https://github.com/artonson/def.

DensePose estimation task is a significant step forward for enhancing user experience computer vision applications ranging from augmented reality to cloth fitting. Existing neural network models capable of solving this task are heavily parameterized and a long way from being transferred to an embedded or mobile device. To enable Dense Pose inference on the end device with current models, one needs to support an expensive server-side infrastructure and have a stable internet connection. To make things worse, mobile and embedded devices do not always have a powerful GPU inside. In this work, we target the problem of redesigning the DensePose R-CNN model's architecture so that the final network retains most of its accuracy but becomes more light-weight and fast. To achieve that, we tested and incorporated many deep learning innovations from recent years, specifically performing an ablation study on 23 efficient backbone architectures, multiple two-stage detection pipeline modifications, and custom model quantization methods. As a result, we achieved 17× model size reduction and 2× latency improvement compared to the baseline model.1