Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors
- URL: http://arxiv.org/abs/2502.07615v1
- Date: Tue, 11 Feb 2025 15:05:26 GMT
- Title: Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors
- Authors: Lin-Zhuo Chen, Kangjie Liu, Youtian Lin, Siyu Zhu, Zhihao Li, Xun Cao, Yao Yao,
- Abstract summary: 3D Gaussian Splatting (3DGS) has achieved excellent rendering quality with fast training and rendering speed.
However, its optimization process lacks explicit geometric constraints, leading to suboptimal geometric reconstruction in regions with sparse or no observational input views.
We introduce Flow Distillation Sampling (FDS), a technique that leverages pre-trained geometric knowledge to bolster the accuracy of the Gaussian radiance field.
- Score: 18.381635530507978
- License:
- Abstract: 3D Gaussian Splatting (3DGS) has achieved excellent rendering quality with fast training and rendering speed. However, its optimization process lacks explicit geometric constraints, leading to suboptimal geometric reconstruction in regions with sparse or no observational input views. In this work, we try to mitigate the issue by incorporating a pre-trained matching prior to the 3DGS optimization process. We introduce Flow Distillation Sampling (FDS), a technique that leverages pre-trained geometric knowledge to bolster the accuracy of the Gaussian radiance field. Our method employs a strategic sampling technique to target unobserved views adjacent to the input views, utilizing the optical flow calculated from the matching model (Prior Flow) to guide the flow analytically calculated from the 3DGS geometry (Radiance Flow). Comprehensive experiments in depth rendering, mesh reconstruction, and novel view synthesis showcase the significant advantages of FDS over state-of-the-art methods. Additionally, our interpretive experiments and analysis aim to shed light on the effects of FDS on geometric accuracy and rendering quality, potentially providing readers with insights into its performance. Project page: https://nju-3dv.github.io/projects/fds
Related papers
- Visual SLAM with 3D Gaussian Primitives and Depth Priors Enabling Novel View Synthesis [11.236094544193605]
Conventional geometry-based SLAM systems lack dense 3D reconstruction capabilities.
We propose a real-time RGB-D SLAM system that incorporates a novel view synthesis technique, 3D Gaussian Splatting.
arXiv Detail & Related papers (2024-08-10T21:23:08Z) - Efficient Depth-Guided Urban View Synthesis [52.841803876653465]
We introduce Efficient Depth-Guided Urban View Synthesis (EDUS) for fast feed-forward inference and efficient per-scene fine-tuning.
EDUS exploits noisy predicted geometric priors as guidance to enable generalizable urban view synthesis from sparse input images.
Our results indicate that EDUS achieves state-of-the-art performance in sparse view settings when combined with fast test-time optimization.
arXiv Detail & Related papers (2024-07-17T08:16:25Z) - Free-SurGS: SfM-Free 3D Gaussian Splatting for Surgical Scene Reconstruction [36.46068581419659]
Real-time 3D reconstruction of surgical scenes plays a vital role in computer-assisted surgery.
Recent advancements in 3D Gaussian Splatting have shown great potential for real-time novel view synthesis.
We propose the first SfM-free 3DGS-based method for surgical scene reconstruction.
arXiv Detail & Related papers (2024-07-03T08:49:35Z) - GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstruction [3.043712258792239]
We present a unified framework integrating neural SDF with 3DGS.
This framework incorporates a learnable neural SDF field to guide the densification and pruning of Gaussians.
Our method achieves state-of-the-art performance in both surface reconstruction and novel view synthesis.
arXiv Detail & Related papers (2024-05-30T03:46:59Z) - SAGS: Structure-Aware 3D Gaussian Splatting [53.6730827668389]
We propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene.
SAGS reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark novel-view synthesis datasets.
arXiv Detail & Related papers (2024-04-29T23:26:30Z) - Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes [50.92217884840301]
Gaussian Opacity Fields (GOF) is a novel approach for efficient, high-quality, and adaptive surface reconstruction in scenes.
GOF is derived from ray-tracing-based volume rendering of 3D Gaussians.
GOF surpasses existing 3DGS-based methods in surface reconstruction and novel view synthesis.
arXiv Detail & Related papers (2024-04-16T17:57:19Z) - GaussianPro: 3D Gaussian Splatting with Progressive Propagation [49.918797726059545]
3DGS relies heavily on the point cloud produced by Structure-from-Motion (SfM) techniques.
We propose a novel method that applies a progressive propagation strategy to guide the densification of the 3D Gaussians.
Our method significantly surpasses 3DGS on the dataset, exhibiting an improvement of 1.15dB in terms of PSNR.
arXiv Detail & Related papers (2024-02-22T16:00:20Z) - 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) - GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting [51.96353586773191]
We introduce textbfGS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping system.
Our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D rendering.
Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets.
arXiv Detail & Related papers (2023-11-20T12:08:23Z)
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.