PoI: A Filter to Extract Pixel of Interest from Novel View Synthesis for Scene Coordinate Regression

• URL: http://arxiv.org/abs/2502.04843v3
• Date: Sat, 28 Jun 2025 10:06:29 GMT
• Title: PoI: A Filter to Extract Pixel of Interest from Novel View Synthesis for Scene Coordinate Regression
• Authors: Feifei Li, Qi Song, Chi Zhang, Hui Shuai, Rui Huang,
• Abstract summary: Novel View Synthesis (NVS) techniques can augment camera pose estimation by extending and diversifying training data.<n>Images generated by these methods are often plagued by spatial artifacts such as blurring and ghosting.<n>We propose a dual-criteria filtering mechanism that dynamically identifies and discards suboptimal pixels during training.
• Score: 28.39136566857838
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Novel View Synthesis (NVS) techniques, notably Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), can augment camera pose estimation by extending and diversifying training data. However, images generated by these methods are often plagued by spatial artifacts such as blurring and ghosting, undermining their reliability as training data for camera pose estimation. This limitation is particularly critical for Scene Coordinate Regression (SCR) methods, which aim at pixel-level 3D coordinate estimation, because rendering artifacts directly lead to estimation inaccuracies. To address this challenge, we propose a dual-criteria filtering mechanism that dynamically identifies and discards suboptimal pixels during training. The dual-criteria filter evaluates two concurrent metrics: (1) real-time SCR reprojection error, and (2) gradient threshold, across the coordinate regression domain. In addition, for visual localization problems in sparse-input scenarios, it becomes even more necessary to use NVS-generated data to assist localization. We design a coarse-to-fine Points of Interest (PoI) variant using sparse-input NVS to solve this problem. Experiments across indoor and outdoor benchmarks confirm our method's efficacy, achieving state-of-the-art localization accuracy while maintaining computational efficiency.

Related papers

• Hi^2-GSLoc: Dual-Hierarchical Gaussian-Specific Visual Relocalization for Remote Sensing [6.997091164331322]
  Visual relocalization is fundamental to remote sensing and UAV applications.<n>Existing methods face inherent trade-offs: image-based retrieval and pose regression approaches lack precision.<n>We introduce $mathrmHi2$-GSLoc, a dual-hierarchical relocalization framework that follows a sparse-to-dense and coarse-to-fine paradigm.
  arXiv  Detail & Related papers  (2025-07-21T14:47:56Z)
• GSplatLoc: Ultra-Precise Camera Localization via 3D Gaussian Splatting [0.0]
  We present GSplatLoc, a camera localization method that leverages the differentiable rendering capabilities of 3D Gaussian splatting for ultra-precise pose estimation.<n> GSplatLoc sets a new benchmark for localization in dense mapping, with important implications for applications requiring accurate real-time localization, such as robotics and augmented reality.
  arXiv  Detail & Related papers  (2024-12-28T07:14:14Z)
• DGTR: Distributed Gaussian Turbo-Reconstruction for Sparse-View Vast Scenes [81.56206845824572]
  Novel-view synthesis (NVS) approaches play a critical role in vast scene reconstruction. Few-shot methods often struggle with poor reconstruction quality in vast environments. This paper presents DGTR, a novel distributed framework for efficient Gaussian reconstruction for sparse-view vast scenes.
  arXiv  Detail & Related papers  (2024-11-19T07:51:44Z)
• FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training [15.634646420318731]
  We present a 3D Gaussian-based novel view synthesis method using sparse input images. We propose a multi-stage training scheme with matching-based consistency constraints imposed on the novel views. This is achieved by using the matches of the available training images to supervise the generation of the novel views.
  arXiv  Detail & Related papers  (2024-11-04T16:21:00Z)
• No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images [100.80376573969045]
  NoPoSplat is a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from multi-view images. Our model achieves real-time 3D Gaussian reconstruction during inference. This work makes significant advances in pose-free generalizable 3D reconstruction and demonstrates its applicability to real-world scenarios.
  arXiv  Detail & Related papers  (2024-10-31T17:58:22Z)
• 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)
• GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization [1.4466437171584356]
  We propose a two-stage procedure that integrates dense and robust keypoint descriptors from the lightweight XFeat feature extractor into 3DGS. In the second stage, the initial pose estimate is refined by minimizing the rendering-based photometric warp loss. Benchmarking on widely used indoor and outdoor datasets demonstrates improvements over recent neural rendering-based localization methods.
  arXiv  Detail & Related papers  (2024-09-24T23:18:32Z)
• SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization [16.460851701725392]
  We present a novel approach that optimize radiance fields with scene graphs to mitigate the influence of outlier poses. Our method incorporates an adaptive inlier-outlier confidence estimation scheme based on scene graphs. We also introduce an effective intersection-over-union (IoU) loss to optimize the camera pose and surface geometry.
  arXiv  Detail & Related papers  (2024-07-17T15:50:17Z)
• A Construct-Optimize Approach to Sparse View Synthesis without Camera Pose [44.13819148680788]
  We develop a novel construct-and-optimize method for sparse view synthesis without camera poses. Specifically, we construct a solution by using monocular depth and projecting pixels back into the 3D world. We demonstrate results on the Tanks and Temples and Static Hikes datasets with as few as three widely-spaced views.
  arXiv  Detail & Related papers  (2024-05-06T17:36:44Z)
• SpikeNVS: Enhancing Novel View Synthesis from Blurry Images via Spike Camera [78.20482568602993]
  Conventional RGB cameras are susceptible to motion blur. Neuromorphic cameras like event and spike cameras inherently capture more comprehensive temporal information. Our design can enhance novel view synthesis across NeRF and 3DGS.
  arXiv  Detail & Related papers  (2024-04-10T03:31:32Z)
• Leveraging Neural Radiance Field in Descriptor Synthesis for Keypoints Scene Coordinate Regression [1.2974519529978974]
  This paper introduces a pipeline for keypoint descriptor synthesis using Neural Radiance Field (NeRF) generating novel poses and feeding them into a trained NeRF model to create new views, our approach enhances the KSCR's capabilities in data-scarce environments. The proposed system could significantly improve localization accuracy by up to 50% and cost only a fraction of time for data synthesis.
  arXiv  Detail & Related papers  (2024-03-15T13:40:37Z)
• Mip-Splatting: Alias-free 3D Gaussian Splatting [52.366815964832426]
  3D Gaussian Splatting has demonstrated impressive novel view synthesis results, reaching high fidelity and efficiency. Strong artifacts can be observed when changing the sampling rate, eg, by changing focal length or camera distance. We find that the source for this phenomenon can be attributed to the lack of 3D frequency constraints and the usage of a 2D dilation filter.
  arXiv  Detail & Related papers  (2023-11-27T13:03:09Z)
• Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localization [56.95046107046027]
  We propose to leverage Neural Radiance Fields (NeRF) to generate training samples for scene coordinate regression. Despite NeRF's efficiency in rendering, many of the rendered data are polluted by artifacts or only contain minimal information gain.
  arXiv  Detail & Related papers  (2023-10-10T20:11:13Z)
• Neural Refinement for Absolute Pose Regression with Feature Synthesis [33.2608395824548]
  Absolute Pose Regression (APR) methods use deep neural networks to directly regress camera poses from RGB images. In this work, we propose a test-time refinement pipeline that leverages implicit geometric constraints. We also introduce a novel Neural Feature Synthesizer (NeFeS) model, which encodes 3D geometric features during training and directly renders dense novel view features at test time to refine APR methods.
  arXiv  Detail & Related papers  (2023-03-17T16:10:50Z)
• CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representations [77.90883737693325]
  This paper proposes CLONeR, which significantly improves upon NeRF by allowing it to model large outdoor driving scenes observed from sparse input sensor views. This is achieved by decoupling occupancy and color learning within the NeRF framework into separate Multi-Layer Perceptrons (MLPs) trained using LiDAR and camera data, respectively. In addition, this paper proposes a novel method to build differentiable 3D Occupancy Grid Maps (OGM) alongside the NeRF model, and leverage this occupancy grid for improved sampling of points along a ray for rendering in metric space.
  arXiv  Detail & Related papers  (2022-09-02T17:44:50Z)
• Progressively-connected Light Field Network for Efficient View Synthesis [69.29043048775802]
  We present a Progressively-connected Light Field network (ProLiF) for the novel view synthesis of complex forward-facing scenes. ProLiF encodes a 4D light field, which allows rendering a large batch of rays in one training step for image- or patch-level losses.
  arXiv  Detail & Related papers  (2022-07-10T13:47:20Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• Feature matching for multi-epoch historical aerial images [0.0]
  We present a fully automatic approach to detecting feature correspondences between historical images taken at different times. Compared to the state-of-the-art, our method improves the image georeferencing accuracy by a factor of 2.
  arXiv  Detail & Related papers  (2021-12-08T12:28:24Z)
• LENS: Localization enhanced by NeRF synthesis [3.4386226615580107]
  We demonstrate improvement of camera pose regression thanks to an additional synthetic dataset rendered by the NeRF class of algorithm. We further improved localization accuracy of pose regressors using synthesized realistic and geometry consistent images as data augmentation during training.
  arXiv  Detail & Related papers  (2021-10-13T08:15:08Z)
• Uncertainty-Aware Camera Pose Estimation from Points and Lines [101.03675842534415]
  Perspective-n-Point-and-Line (Pn$PL) aims at fast, accurate and robust camera localizations with respect to a 3D model from 2D-3D feature coordinates.
  arXiv  Detail & Related papers  (2021-07-08T15:19:36Z)

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.