BRUM: Robust 3D Vehicle Reconstruction from 360 Sparse Images
- URL: http://arxiv.org/abs/2507.12095v1
- Date: Wed, 16 Jul 2025 10:04:35 GMT
- Title: BRUM: Robust 3D Vehicle Reconstruction from 360 Sparse Images
- Authors: Davide Di Nucci, Matteo Tomei, Guido Borghi, Luca Ciuffreda, Roberto Vezzani, Rita Cucchiara,
- Abstract summary: This paper addresses the challenge of reconstructing vehicles from sparse-view inputs.<n>We leverage depth maps and a robust pose estimation architecture to synthesize novel views.<n>We present a novel dataset featuring both synthetic and real-world public transportation vehicles.
- Score: 21.811586185200706
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Accurate 3D reconstruction of vehicles is vital for applications such as vehicle inspection, predictive maintenance, and urban planning. Existing methods like Neural Radiance Fields and Gaussian Splatting have shown impressive results but remain limited by their reliance on dense input views, which hinders real-world applicability. This paper addresses the challenge of reconstructing vehicles from sparse-view inputs, leveraging depth maps and a robust pose estimation architecture to synthesize novel views and augment training data. Specifically, we enhance Gaussian Splatting by integrating a selective photometric loss, applied only to high-confidence pixels, and replacing standard Structure-from-Motion pipelines with the DUSt3R architecture to improve camera pose estimation. Furthermore, we present a novel dataset featuring both synthetic and real-world public transportation vehicles, enabling extensive evaluation of our approach. Experimental results demonstrate state-of-the-art performance across multiple benchmarks, showcasing the method's ability to achieve high-quality reconstructions even under constrained input conditions.
Related papers
- RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions [67.48495052903534]
We propose a general and efficient multi-view feature enhancement module, RobustGS.<n>It substantially improves the robustness of feedforward 3DGS methods under various adverse imaging conditions.<n>The RobustGS module can be seamlessly integrated into existing pretrained pipelines in a plug-and-play manner.
arXiv Detail & Related papers (2025-08-05T04:50:29Z) - GTR: Gaussian Splatting Tracking and Reconstruction of Unknown Objects Based on Appearance and Geometric Complexity [49.31257173003408]
We present a novel method for 6-DoF object tracking and high-quality 3D reconstruction from monocular RGBD video.<n>Our approach demonstrates strong capabilities in recovering high-fidelity object meshes, setting a new standard for single-sensor 3D reconstruction in open-world environments.
arXiv Detail & Related papers (2025-05-17T08:46:29Z) - A Survey of 3D Reconstruction with Event Cameras [16.103940503726022]
Event cameras produce sparse yet temporally dense data streams, enabling robust and accurate 3D reconstruction.<n>These capabilities offer substantial promise for transformative applications across various fields, including autonomous driving, robotics, aerial navigation, and immersive virtual reality.<n>This survey aims to serve as an essential reference and provides a clear and motivating roadmap toward advancing the state of the art in event-driven 3D reconstruction.
arXiv Detail & Related papers (2025-05-13T11:04:04Z) - A self-supervised cyclic neural-analytic approach for novel view synthesis and 3D reconstruction [11.558827428811385]
We propose a self-supervised cyclic neural-analytic pipeline that combines high-quality neural rendering outputs with precise geometric insights from analytical methods.<n>Our solution improves RGB and mesh reconstructions for novel view synthesis, especially in undersampled areas and regions that are completely different from the training dataset.<n>Our findings demonstrate substantial improvements in rendering views of novel and also 3D reconstruction, which to the best of our knowledge is a first.
arXiv Detail & Related papers (2025-03-05T14:28:01Z) - FlexDrive: Toward Trajectory Flexibility in Driving Scene Reconstruction and Rendering [79.39246982782717]
We introduce an Inverse View Warping technique to create compact and high-quality images as supervision for the reconstruction of the out-of-path views.<n>Our method achieves superior in-path and out-of-path reconstruction and rendering performance on the widely used Open dataset.
arXiv Detail & Related papers (2025-02-28T14:32:04Z) - PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices.
Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
arXiv Detail & Related papers (2024-10-29T15:28:15Z) - Drone-assisted Road Gaussian Splatting with Cross-view Uncertainty [10.37108303188536]
3D Gaussian Splatting (3D-GS) has made groundbreaking progress in neural rendering.
The general fidelity of large-scale road scene renderings is often limited by the input imagery.
We introduce the cross-view uncertainty to 3D-GS by matching the car-view ensemble-based rendering uncertainty to aerial images.
arXiv Detail & Related papers (2024-08-27T17:59:55Z) - Accurate Cross-modal Reconstruction of Vehicle Target from Sparse-aspect Multi-baseline SAR data [5.757535707973869]
Multi-aspect multi-baseline SAR 3D imaging is a critical remote sensing technique, promising in urban mapping and monitoring.<n>In the past, compressive sensing (CS) was the mainstream approach for sparse 3D SAR reconstruction.<n>Deep learning (DL) has emerged as a powerful alternative, markedly boosting reconstruction quality and efficiency.
arXiv Detail & Related papers (2024-06-06T15:18:59Z) - CarPatch: A Synthetic Benchmark for Radiance Field Evaluation on Vehicle
Components [77.33782775860028]
We introduce CarPatch, a novel synthetic benchmark of vehicles.
In addition to a set of images annotated with their intrinsic and extrinsic camera parameters, the corresponding depth maps and semantic segmentation masks have been generated for each view.
Global and part-based metrics have been defined and used to evaluate, compare, and better characterize some state-of-the-art techniques.
arXiv Detail & Related papers (2023-07-24T11:59:07Z) - Neural 3D Reconstruction in the Wild [86.6264706256377]
We introduce a new method that enables efficient and accurate surface reconstruction from Internet photo collections.
We present a new benchmark and protocol for evaluating reconstruction performance on such in-the-wild scenes.
arXiv Detail & Related papers (2022-05-25T17:59:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.