arXiv subjects

Preet Savalia

Publications and source records attributed to Preet Savalia.

3 recordsLinked to original sources

arXiv2026

MB-Loc: Multi-planar Bird's-eye-view Localization in outdoor LiDAR scenes

Global LiDAR localization is a fundamental task for autonomous navigation systems. Recent methods perform Scene Coordinate Regression (SCR) and achieve superior accuracy over Absolute Pose Regression (APR) solutions by predicting dense 3D world coordinates. However, SCR approaches introduce two major bottlenecks: severe computational inefficiency from processing raw 3D geometries and significant performance degradation under varying sensor viewpoints. To address these limitations, we present MB-Loc, a lightweight and viewpoint-robust SCR framework. Instead of relying on heavy 3D convolutions, we project the input LiDAR scan into a 2.5D Multi-planar Bird's-Eye View (BEV) representation. By slicing the point-cloud along the Z-axis and mapping signed depths into discrete 2D planes, MB-Loc retains essential 3D geometric structures while exploiting the computational tractability of standard 2D CNNs. To handle the inherent sparsity of outdoor LiDAR, we introduce a KL-regularized latent bottleneck that explicitly models spatial uncertainty without injecting stochastic noise. Finally, to ensure rotation robustness, we apply 3D spatial augmentations prior to planar projection, forcing the network to implicitly learn viewpoint-invariant features. We perform extensive experiments on the publicly available NCLT dataset and demonstrate that our proposed method outperforms the current state-of-the-art. Operating at real-time inference speeds, MB-Loc significantly outperforms traditional 3D-SCR architectures in computational efficiency.

cs.CV↗

arXiv2026

Fast and Robust Mesh Simplification for Generated and Real-World 3D Assets

The rapid growth of 3D content from modern reconstruction and generative pipelines, such as neural rendering and large-scale 3D asset generation, has led to an abundance of dense, noisy, and often non-manifold meshes. While these representations achieve high visual fidelity, their complexity poses significant challenges for downstream applications in simulation, AR/VR, and scientific computing, where efficient and reliable geometry is essential. This necessitates mesh simplification methods that are not only fast and robust to "in-the-wild" inputs, but also capable of preserving fine geometric structures and high-quality appearance. In this paper, we propose Feature-Aware Quadric Error Metric (FA-QEM), a comprehensive mesh simplification pipeline designed for modern 3D assets. Our approach introduces a novel multi-term quadric error formulation that jointly encodes geometric deviation, boundary curvature, and surface normal consistency, enabling optimal vertex placement that preserves sharp features even under aggressive simplification. Furthermore, we show that high-fidelity geometric simplification significantly improves downstream appearance transfer, serving as a superior front-end for texture mapping via successive mapping techniques. We conduct extensive evaluations on both AI-generated meshes and large-scale real-world datasets, including Thingi10K and the Real-World Textured Things dataset. Our results demonstrate that FA-QEM achieves consistently lower geometric error, better visual fidelity, and substantially faster runtimes compared to existing methods, while maintaining robustness across diverse and challenging inputs. These properties make FA-QEM a practical and effective component for scalable 3D reconstruction and generation pipelines.

cs.GR↗

arXiv2025

NGD: Neural Gradient Based Deformation for Monocular Garment Reconstruction

Dynamic garment reconstruction from monocular video is an important yet challenging task due to the complex dynamics and unconstrained nature of the garments. Recent advancements in neural rendering have enabled high-quality geometric reconstruction with image/video supervision. However, implicit representation methods that use volume rendering often provide smooth geometry and fail to model high-frequency details. While template reconstruction methods model explicit geometry, they use vertex displacement for deformation, which results in artifacts. Addressing these limitations, we propose NGD, a Neural Gradient-based Deformation method to reconstruct dynamically evolving textured garments from monocular videos. Additionally, we propose a novel adaptive remeshing strategy for modelling dynamically evolving surfaces like wrinkles and pleats of the skirt, leading to high-quality reconstruction. Finally, we learn dynamic texture maps to capture per-frame lighting and shadow effects. We provide extensive qualitative and quantitative evaluations to demonstrate significant improvements over existing SOTA methods and provide high-quality garment reconstructions.

cs.CV↗