Evaluating saliency scores in point clouds of natural environments by learning surface anomalies

• URL: http://arxiv.org/abs/2408.14421v1
• Date: Mon, 26 Aug 2024 17:04:52 GMT
• Title: Evaluating saliency scores in point clouds of natural environments by learning surface anomalies
• Authors: Reuma Arav, Dennis Wittich, Franz Rottensteiner,
• Abstract summary: We propose to differentiate objects of interest from the cluttered environment by evaluating how much they stand out from their surroundings. Previous saliency detection approaches suggested mostly handcrafted attributes for the task. Here we propose a learning-based mechanism that accommodates noise and textured surfaces.
• Score: 0.2340830801548167
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, three-dimensional point clouds are used increasingly to document natural environments. Each dataset contains a diverse set of objects, at varying shapes and sizes, distributed throughout the data and intricately intertwined with the topography. Therefore, regions of interest are difficult to find and consequent analyses become a challenge. Inspired from visual perception principles, we propose to differentiate objects of interest from the cluttered environment by evaluating how much they stand out from their surroundings, i.e., their geometric salience. Previous saliency detection approaches suggested mostly handcrafted attributes for the task. However, such methods fail when the data are too noisy or have high levels of texture. Here we propose a learning-based mechanism that accommodates noise and textured surfaces. We assume that within the natural environment any change from the prevalent surface would suggest a salient object. Thus, we first learn the underlying surface and then search for anomalies within it. Initially, a deep neural network is trained to reconstruct the surface. Regions where the reconstructed part deviates significantly from the original point cloud yield a substantial reconstruction error, signifying an anomaly, i.e., saliency. We demonstrate the effectiveness of the proposed approach by searching for salient features in various natural scenarios, which were acquired by different acquisition platforms. We show the strong correlation between the reconstruction error and salient objects.

Related papers

• ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction [50.07671826433922]
  It is non-trivial to simultaneously recover meticulous geometry and preserve smoothness across regions with differing characteristics. We propose ND-SDF, which learns a Normal Deflection field to represent the angular deviation between the scene normal and the prior normal. Our method not only obtains smooth weakly textured regions such as walls and floors but also preserves the geometric details of complex structures.
  arXiv  Detail & Related papers  (2024-08-22T17:59:01Z)
• InfoNorm: Mutual Information Shaping of Normals for Sparse-View Reconstruction [15.900375207144759]
  3D surface reconstruction from multi-view images is essential for scene understanding and interaction. Recent implicit surface representations, such as Neural Radiance Fields (NeRFs) and signed distance functions (SDFs) employ various geometric priors to resolve the lack of observed information. We propose regularizing the geometric modeling by explicitly encouraging the mutual information among surface normals of highly correlated scene points.
  arXiv  Detail & Related papers  (2024-07-17T15:46:25Z)
• Explicitly Disentangled Representations in Object-Centric Learning [0.0]
  We propose a novel architecture that biases object-centric models toward disentangling shape and texture components. In particular, we propose a novel architecture that biases object-centric models toward disentangling shape and texture components.
  arXiv  Detail & Related papers  (2024-01-18T17:22:11Z)
• A Survey and Benchmark of Automatic Surface Reconstruction from Point Clouds [12.58355339505807]
  We present both traditional and learning-based methods for surface reconstruction from point clouds. Traditional approaches often simplify the problem by imposing handcrafted priors on either the input point clouds or the resulting surface. Deep learning models have the capability directly learn the properties of input point clouds.
  arXiv  Detail & Related papers  (2023-01-31T14:18:19Z)
• Robust Change Detection Based on Neural Descriptor Fields [53.111397800478294]
  We develop an object-level online change detection approach that is robust to partially overlapping observations and noisy localization results. By associating objects via shape code similarity and comparing local object-neighbor spatial layout, our proposed approach demonstrates robustness to low observation overlap and localization noises.
  arXiv  Detail & Related papers  (2022-08-01T17:45:36Z)
• Discovering Objects that Can Move [55.743225595012966]
  We study the problem of object discovery -- separating objects from the background without manual labels. Existing approaches utilize appearance cues, such as color, texture, and location, to group pixels into object-like regions. We choose to focus on dynamic objects -- entities that can move independently in the world.
  arXiv  Detail & Related papers  (2022-03-18T21:13:56Z)
• SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements [62.652588951757764]
  Learning to model and reconstruct humans in clothing is challenging due to articulation, non-rigid deformation, and varying clothing types and topologies. Recent work uses neural networks to parameterize local surface elements. We present three key innovations: First, we deform surface elements based on a human body model. Second, we address the limitations of existing neural surface elements by regressing local geometry from local features.
  arXiv  Detail & Related papers  (2021-04-15T17:59:39Z)
• Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds [35.80493796701116]
  We propose to learn a local implicit surface network for a shared, adaptive modeling of the entire surface of an object. We also enhance the leveraging of surface self-similarities by improving correlations among the optimized latent codes of individual surface patches. We term our framework as Sign-Agnostic Implicit Learning of Surface Self-Similarities (SAIL-S3)
  arXiv  Detail & Related papers  (2020-12-14T13:33:22Z)
• RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction [19.535169371240073]
  We introduce RfD-Net that jointly detects and reconstructs dense object surfaces directly from point clouds. We decouple the instance reconstruction into global object localization and local shape prediction. Our approach consistently outperforms the state-of-the-arts and improves over 11 of mesh IoU in object reconstruction.
  arXiv  Detail & Related papers  (2020-11-30T12:58:05Z)
• Deep Structured Prediction for Facial Landmark Detection [59.60946775628646]
  This paper proposes a method for deep structured facial landmark detection based on combining a deep Convolutional Network with a Conditional Random Field. We demonstrate its superior performance to existing state-of-the-art techniques in facial landmark detection.
  arXiv  Detail & Related papers  (2020-10-18T17:09:24Z)
• Latent World Models For Intrinsically Motivated Exploration [140.21871701134626]
  We present a self-supervised representation learning method for image-based observations. We consider episodic and life-long uncertainties to guide the exploration of partially observable environments.
  arXiv  Detail & Related papers  (2020-10-05T19:47:04Z)

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.