ClaraVid: A Holistic Scene Reconstruction Benchmark From Aerial Perspective With Delentropy-Based Complexity Profiling

• URL: http://arxiv.org/abs/2503.17856v2
• Date: Thu, 31 Jul 2025 16:56:06 GMT
• Title: ClaraVid: A Holistic Scene Reconstruction Benchmark From Aerial Perspective With Delentropy-Based Complexity Profiling
• Authors: Radu Beche, Sergiu Nedevschi,
• Abstract summary: We introduce ClaraVid, a synthetic aerial dataset specifically designed to overcome limitations of existing datasets.<n>The dataset consists of 16,917 high-resolution images captured at 4032x3024 from multiple viewpoints across diverse landscapes.<n>To further advance neural reconstruction, we introduce the Delentropic Scene Profile (DSP), a novel complexity metric derived from differential entropy analysis.
• Score: 5.6168844664788855
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The development of aerial holistic scene understanding algorithms is hindered by the scarcity of comprehensive datasets that enable both semantic and geometric reconstruction. While synthetic datasets offer an alternative, existing options exhibit task-specific limitations, unrealistic scene compositions, and rendering artifacts that compromise real-world applicability. We introduce ClaraVid, a synthetic aerial dataset specifically designed to overcome these limitations. Comprising 16,917 high-resolution images captured at 4032x3024 from multiple viewpoints across diverse landscapes, ClaraVid provides dense depth maps, panoptic segmentation, sparse point clouds, and dynamic object masks, while mitigating common rendering artifacts. To further advance neural reconstruction, we introduce the Delentropic Scene Profile (DSP), a novel complexity metric derived from differential entropy analysis, designed to quantitatively assess scene difficulty and inform reconstruction tasks. Utilizing DSP, we systematically benchmark neural reconstruction methods, uncovering a consistent, measurable correlation between scene complexity and reconstruction accuracy. Empirical results indicate that higher delentropy strongly correlates with increased reconstruction errors, validating DSP as a reliable complexity prior. The data and code are available on the project page at https://rdbch.github.io/claravid/

Related papers

• DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion [59.25479674775212]
  DepR is a depth-guided single-view scene reconstruction framework.<n>It generates individual objects and composes them into a coherent 3D layout.<n>It achieves state-of-the-art performance despite being trained on limited synthetic data.
  arXiv  Detail & Related papers  (2025-07-30T16:40:46Z)
• Real-Time Scene Reconstruction using Light Field Probes [2.283090308443312]
  Reconstructing photo-realistic large-scale scenes from images is a long-standing problem in computer graphics.<n>Our work explores novel view synthesis methods that efficiently reconstruct complex scenes without explicit use of scene geometries.<n>Our approach can potentially be applied to virtual reality (VR) and augmented reality (AR) applications.
  arXiv  Detail & Related papers  (2025-07-19T13:43:30Z)
• Learning Fine-Grained Geometry for Sparse-View Splatting via Cascade Depth Loss [15.425094458647933]
  We introduce Hierarchical Depth-Guided Splatting (HDGS), a depth supervision framework that progressively refines geometry from coarse to fine levels.<n>By enforcing multi-scale depth consistency, our method substantially improves structural fidelity in sparse-view scenarios.
  arXiv  Detail & Related papers  (2025-05-28T12:16:42Z)
• Decompositional Neural Scene Reconstruction with Generative Diffusion Prior [64.71091831762214]
  Decompositional reconstruction of 3D scenes, with complete shapes and detailed texture, is intriguing for downstream applications.<n>Recent approaches incorporate semantic or geometric regularization to address this issue, but they suffer significant degradation in underconstrained areas.<n>We propose DP-Recon, which employs diffusion priors in the form of Score Distillation Sampling (SDS) to optimize the neural representation of each individual object under novel views.
  arXiv  Detail & Related papers  (2025-03-19T02:11:31Z)
• SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantification [0.0]
  We present a neural radiance field (NeRF) based large-scale reconstruction system that fuses lidar and vision data.<n>Our system adopts the state-of-the-art NeRF representation to additionally incorporate lidar.<n>We demonstrate the reconstruction system using a multi-camera, lidar sensor suite in experiments involving both robot-mounted and handheld scanning.
  arXiv  Detail & Related papers  (2025-02-04T19:00:49Z)
• SMORE: Simultaneous Map and Object REconstruction [66.66729715211642]
  We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR.<n>We take a holistic perspective and optimize a compositional model of a dynamic scene that decomposes the world into rigidly-moving objects and the background.
  arXiv  Detail & Related papers  (2024-06-19T23:53:31Z)
• Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction [51.3632308129838]
  We present Total-Decom, a novel method for decomposed 3D reconstruction with minimal human interaction. Our approach seamlessly integrates the Segment Anything Model (SAM) with hybrid implicit-explicit neural surface representations and a mesh-based region-growing technique for accurate 3D object decomposition. We extensively evaluate our method on benchmark datasets and demonstrate its potential for downstream applications, such as animation and scene editing.
  arXiv  Detail & Related papers  (2024-03-28T11:12:33Z)
• AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation [51.143540967290114]
  We propose a method that unlocks a wide range of previously-infeasible geometric augmentations for unsupervised depth computation and estimation. This is achieved by reversing, or undo''-ing, geometric transformations to the coordinates of the output depth, warping the depth map back to the original reference frame.
  arXiv  Detail & Related papers  (2023-10-15T05:15:45Z)
• Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering [93.94371335579321]
  We propose a learning framework that trains models to predict geometry-preserving depth without requiring extra data or annotations. Comprehensive experiments underscore our framework's superior generalization capabilities. Our innovative loss functions empower the model to autonomously recover domain-specific scale-and-shift coefficients.
  arXiv  Detail & Related papers  (2023-09-18T12:36:39Z)
• Point Scene Understanding via Disentangled Instance Mesh Reconstruction [21.92736190195887]
  We propose aDisentangled Instance Mesh Reconstruction (DIMR) framework for effective point scene understanding. A segmentation-based backbone is applied to reduce false positive object proposals. We leverage a mesh-aware latent code space to disentangle the processes of shape completion and mesh generation.
  arXiv  Detail & Related papers  (2022-03-31T06:36:07Z)
• SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion [86.77318031029404]
  We propose a framework that performs scene reconstruction and semantic scene completion jointly in an incremental and real-time manner. Our framework relies on a novel neural architecture designed to process occupancy maps and leverages voxel states to accurately and efficiently fuse semantic completion with the 3D global model.
  arXiv  Detail & Related papers  (2020-10-26T15:31:52Z)
• 3D Dense Geometry-Guided Facial Expression Synthesis by Adversarial Learning [54.24887282693925]
  We propose a novel framework to exploit 3D dense (depth and surface normals) information for expression manipulation. We use an off-the-shelf state-of-the-art 3D reconstruction model to estimate the depth and create a large-scale RGB-Depth dataset. Our experiments demonstrate that the proposed method outperforms the competitive baseline and existing arts by a large margin.
  arXiv  Detail & Related papers  (2020-09-30T17:12:35Z)

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.