Pi-GS: Sparse-View Gaussian Splatting with Dense π^3 Initialization

• URL: http://arxiv.org/abs/2602.03327v1
• Date: Tue, 03 Feb 2026 09:55:03 GMT
• Title: Pi-GS: Sparse-View Gaussian Splatting with Dense π^3 Initialization
• Authors: Manuel Hofer, Markus Steinberger, Thomas Köhler,
• Abstract summary: We propose a robust method utilizing 3, a reference-free point cloud estimation network.<n>We employ uncertainty-guided depth supervision, normal consistency loss, and depth warping.<n>Our approach achieves state-of-the-art performance on the Tanks and Temples, LLFF, DTU, and MipNeRF360 datasets.
• Score: 5.5775900281150514
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Novel view synthesis has evolved rapidly, advancing from Neural Radiance Fields to 3D Gaussian Splatting (3DGS), which offers real-time rendering and rapid training without compromising visual fidelity. However, 3DGS relies heavily on accurate camera poses and high-quality point cloud initialization, which are difficult to obtain in sparse-view scenarios. While traditional Structure from Motion (SfM) pipelines often fail in these settings, existing learning-based point estimation alternatives typically require reliable reference views and remain sensitive to pose or depth errors. In this work, we propose a robust method utilizing π^3, a reference-free point cloud estimation network. We integrate dense initialization from π^3 with a regularization scheme designed to mitigate geometric inaccuracies. Specifically, we employ uncertainty-guided depth supervision, normal consistency loss, and depth warping. Experimental results demonstrate that our approach achieves state-of-the-art performance on the Tanks and Temples, LLFF, DTU, and MipNeRF360 datasets.

Related papers

• Extreme Views: 3DGS Filter for Novel View Synthesis from Out-of-Distribution Camera Poses [3.007949058551534]
  When viewing a 3D Gaussian Splatting (3DGS) model from camera positions significantly outside the training data distribution, substantial visual noise commonly occurs.<n>We propose a novel real-time render-aware filtering method to address this issue.<n>Our method substantially improves visual quality, realism, and consistency compared to existing Neural Radiance Field (NeRF)-based approaches.
  arXiv  Detail & Related papers  (2025-10-22T21:09:16Z)
• Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline [64.42938561167402]
  We propose an online 3D reconstruction method using 3D Gaussian-based SLAM, combined with a feed-forward recurrent prediction module.<n>This approach replaces slow test-time optimization with fast network inference, significantly improving tracking speed.<n>Our method achieves performance on par with the state-of-the-art SplaTAM, while reducing tracking time by more than 90%.
  arXiv  Detail & Related papers  (2025-08-06T16:16:58Z)
• Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting [57.43483622778394]
  We introduce PM-Loss, a novel regularization loss based on a pointmap predicted by a pre-trained transformer.<n>With the improved depth map, our method significantly improves the feed-forward 3DGS across various architectures and scenes.
  arXiv  Detail & Related papers  (2025-06-05T17:58:23Z)
• Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting [95.61137026932062]
  Intern-GS is a novel approach to enhance the process of sparse-view Gaussian splatting.<n>We show that Intern-GS achieves state-of-the-art rendering quality across diverse datasets.
  arXiv  Detail & Related papers  (2025-05-27T05:17:49Z)
• NexusGS: Sparse View Synthesis with Epipolar Depth Priors in 3D Gaussian Splatting [45.18382361038417]
  We present NexusGS, a 3DGS-based approach that enhances novel view synthesis from sparse-view images.<n>Our method introduces a novel point cloud densification strategy that initializes 3DGS with a dense point cloud.<n> Experiments demonstrate that NexusGS significantly enhances depth accuracy and rendering quality, surpassing state-of-the-art methods by a considerable margin.
  arXiv  Detail & Related papers  (2025-03-24T15:40:17Z)
• 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.<n>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)
• MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views [27.47491233656671]
  Novel View Synthesis (NVS) is a significant challenge in 3D vision applications. We propose textbfMVPGS, a few-shot NVS method that excavates the multi-view priors based on 3D Gaussian Splatting. Experiments show that the proposed method achieves state-of-the-art performance with real-time rendering speed.
  arXiv  Detail & Related papers  (2024-09-22T05:07:20Z)
• LoopSparseGS: Loop Based Sparse-View Friendly Gaussian Splatting [18.682864169561498]
  LoopSparseGS is a loop-based 3DGS framework for the sparse novel view synthesis task. We introduce a novel Sparse-friendly Sampling (SFS) strategy to handle oversized Gaussian ellipsoids leading to large pixel errors. Experiments on four datasets demonstrate that LoopSparseGS outperforms existing state-of-the-art methods for sparse-input novel view synthesis.
  arXiv  Detail & Related papers  (2024-08-01T03:26:50Z)
• FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting [58.41056963451056]
  We propose a few-shot view synthesis framework based on 3D Gaussian Splatting. This framework enables real-time and photo-realistic view synthesis with as few as three training views. FSGS achieves state-of-the-art performance in both accuracy and rendering efficiency across diverse datasets.
  arXiv  Detail & Related papers  (2023-12-01T09:30:02Z)
• Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction [87.08227378010874]
  We show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces a simple geometric constraint, we significantly improve the accuracy and robustness of monocular depth estimation. We show state-of-the-art results of learning metric depth on NYU Depth-V2 and KITTI.
  arXiv  Detail & Related papers  (2021-03-07T00:08:21Z)

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.