Jul 2026· 2026 6th International Conference on Electrical, Computer and Energy Technologies (ICECET)· pp. 1-8· 0 citations· 28 references
Computer Science
TL;DR
The proposed approach leverages 3D Foundation Models for camera pose and pointcloud initialization, then jointly optimizes both camera poses and Gaussian primitives using a depth-guided loss function to enable fast convergence even from rough initialization with as few as 50-60 input views.
Abstract
This paper introduces a fast method for high-quality 3D Gaussian Splatting (3DGS) reconstruction without traditional Structure-from-Motion (SfM). The proposed approach leverages 3D Foundation Models (3DFMs) for camera pose and pointcloud initialization, then jointly optimizes both camera poses and Gaussian primitives using a depth-guided loss function. This enables fast convergence even from rough initialization with as few as 50-60 input views. To further improve reconstruction quality in sparse-view scenarios, an MLP-based pose refinement module is introduced alongside depth-guided supervision from the foundation model. Extensive experiments on Mip-NeRF 360, Tanks and Temples, and RobustNeRF demonstrate that the proposed method achieves competitive reconstruction quality (23.61 dB PSNR, 0.19 LPIPS) while reducing training time to approximately three minutes per scene. The proposed method produces ready-to-use 3DGS models at a fraction of the time required by existing pipelines, making it suitable for near realtime applications in robotics, VR, and autonomous navigation.
Neural radiance fields (NeRF) and 3D Gaussian Splatting (3DGS) are popular techniques to reconstruct and render photorealistic images. However, the prerequisite of running Structure-from-Motion (SfM) to get camera poses limits their completeness. Although previous methods can reconstruct a few unposed images, they are not applicable when images are unordered or densely captured. In this work, we propose a method to train 3DGS from unposed images. Our method leverages a pre-trained 3D geometric foundation model as the neural scene representation. Since the accuracy of the predicted pointmaps does not suffice for accurate image registration and high-fidelity image rendering, we propose to mitigate the issue by initializing and fine-tuning the pre-trained model from a seed image. The images are then progressively registered and added to the training buffer, which is used to train the model further. We also propose to refine the camera poses and pointmaps by minimizing a point-to-camera ray consistency loss across multiple views. When evaluated on diverse challenging datasets, our method outperforms state-of-the-art pose-free NeRF/3DGS methods in terms of both camera pose
Yu Chen, Rolandos Alexandros Potamias, Evangelos Ververas et al.· Advances in Neural Informati...· 0 citations
A semantic-guided 3D Gaussian splatting (3DGS) framework tailored to sparse-view industrial reconstruction was introduced, enabling robust reconstruction from limited viewpoints and offers a practical geometric foundation for automated inspection and remote equipment monitoring.
Boyang Li, Tianhan Gao, Zuan Gu et al.· Visual Computing for Industr...· 0 citations
Abstract. In recent years, Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have emerged as advanced methods for photogrammetry-based 3D reconstruction. Since its introduction in 2020, NeRF has gained significant attention due to its capability to generate high-fidelity reconstructions from multi-view imagery. More recently, 3D Gaussian Splatting (3DGS), introduced in 2023, has proposed an alternative explicit scene representation based on a collection of anisotropic Gaussian primitives optimized directly in 3D space. This representation allows efficient rendering and scalable modelling of complex scenes while maintaining high visual quality. This paper analyses the performance of different 3DGS methods when dealing with complex geometry and less-cooperative surfaces compared to standard SfM IM procedures. Included in the comparison is also the Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction (MILo), a novel meshing method using Gaussian splats. Three Gaussian splatting methods as implemented in the Postshot commercial software were also tested. Our experiments show that MILo shows very promising results in terms of detail reconstruction, while standard Gaussian splatting excels in visualisation but is still plagued by a high rate of noise especially when converted into a geometric point cloud form.
S. Gonizzi Barsanti, D. Billi, E. Sommer et al.· The International Archives o...· 0 citations
Recent advances in 3D reconstruction using mobile cameras have expanded their potential applications beyond traditional domains such as surveying and virtual reality, extending to a wide range of industries. In particular, 3D Gaussian Splatting (3DGS), which can generate photorealistic novel view synthesis from video captured with off-the-shelf RGB cameras, shows promise for industrial use cases involving mobile camera systems that collect images in real time. However, pipelines based on offline Structure-from-Motion (SfM), e.g., COLMAP, are computationally expensive and thus limit practical deployment. While neural network–based acceleration methods have emerged, they are typically limited to processing a small number of input frames, constraining both reconstruction accuracy and spatial coverage. This paper proposes a framework for efficient incremental optimization of 3DGS models. Our framework enables fast and effective fine-tuning by adaptively adjusting the camera poses for additional image frames based on the relationship between L1 and SSIM rendering losses used for 3DGS optimization. Applied to rapidly initialized 3DGS models, our approach achieves a 24% relative improvement in SSIM with just 120 seconds of additional optimization on the Mip-NeRF360 dataset.
Standard 3D Gaussian Splatting (3DGS) pipelines for Novel View Synthesis (NVS) are bottlenecked by Structurefrom-Motion (SfM) initialization. In casual, sparse-view scenarios, feature matching breaks down, causing the entire reconstruction process to fail. We replace this brittle dependency with a COLMAP-free, feed-forward initializer powered by a Visual Geometry Grounded Transformer (VGGT). By leveraging VGGT, our pipeline jointly estimates camera parameters and dense scene geometry across all views in a single pass. A Bridge Module then robustly normalizes the scene scale and conditions initial Gaussian opacity on geometric confidence to discourage floater artifacts during densification. Our framework reduces the initialization phase from minutes (full-scene SfM) to seconds and achieves $\mathbf{1 0 0} \boldsymbol{\%}$ initialization success from as few as three unposed images (a regime where COLMAP succeeds on only 1 of 7 Mip-NeRF 360 scenes). Project page: https://github.com/yuvanrajkrishna/VGGT-Sparse-3DGS.
Shreeya Venkatraman, Yuvan Raj Krishna, J. C. V.· International Conference on...· 0 citations
3D Gaussian Splatting (3DGS) has become the method of choice for reconstructing and real-time rendering of captured scenes. To capture a scene with good visual quality, continuous image sequences are usually combined with out-of-order shots for better scene coverage. Structure from motion can reconstruct such captures, but only after they are all available and often with high computational cost. Incremental reconstruction methods – often derived from SLAM solutions – provide immediate feedback, but cannot handle the out-of-order capture we require. We provide the first immediate feedback solution for such radiance field capture that provides global consistency. We first introduce a method for fast matching in out-of-order sequences, by repurposing visual place recognition models and a covisibility graph, and provide an efficient way to find highly connected keyframes, improving quality even for ordered sequences. We show how these steps – together with GPU optimization and careful Gaussian primitive placement – provide fast local reconstruction, in our challenging radiance field reconstruction case. We then introduce a novel cluster-based method, again using the covisibility graph, to provide efficient loop closure that does not require sequential input. Finally, to handle large scenes in our context, we introduce a progressive hierarchy that allows our method to scale to large environments, without compromising efficiency. Our results show we provide immediate feedback 3DGS reconstruction with good visual quality in several datasets, with up to thousands of input images.
Andréas Meuleman, Linus Franke, Boris Zhestiankin et al.· International Conference on...· 0 citations
