SiZeUp: Fast 3D Proxy from Aerial Images via Depth Ordinal Loss

• URL: http://arxiv.org/abs/2608.22821v2
• Date: Tue, 25 Aug 2026 05:23:29 GMT
• Title: SiZeUp: Fast 3D Proxy from Aerial Images via Depth Ordinal Loss
• Abstract summary: SiZeUp is a fast and scalable approach for constructing large-scale 3D urban proxy models directly from oblique aerial imagery.<n>Our approach achieves a 23-52$times$ speedup over state-of-the-art proxy reconstruction pipelines.
• Score: 45.254340705755
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present SiZeUp, a fast and scalable approach for constructing large-scale 3D urban proxy models directly from calibrated oblique aerial imagery. Our method adopts a height-from-footprint representation, reducing 3D building abstraction to a low-dimensional optimization problem in which building footprints are extruded by a single height parameter. To enable efficient and robust height estimation, we introduce an ordinal depth consistency loss that enforces agreement between the relative depth ordering of rendered proxies and depth priors predicted by a monocular depth model. This is realized through a differentiable renderer that maps parametric building proxies into multi-view depth images, allowing gradients to be propagated from depth supervision to building heights. Our ordinal formulation produces stable optimization in practice and avoids explicit feature matching or dense point cloud reconstruction. Rather than relying on metric depth, which can be unreliable under monocular scale ambiguity, our ordinal depth consistency loss operates on relative depths, providing a more reliable signal across views. Combined with an efficient dynamic view selection, our approach achieves a 23-52$\times$ speedup over state-of-the-art proxy reconstruction pipelines while maintaining comparable proxy-level coverage and volume consistency, making it well suited for large-scale urban modeling tasks.

Related papers

• Large Depth Completion Model from Sparse Observations [28.01552819701954]
  Large Depth Completion Model (LDCM) is a simple, effective, and robust framework for single-view metric depth estimation with sparse observations.<n>LDCM generates metric-accurate dense depth maps using a transformer.
  arXiv  Detail & Related papers  (2026-05-28T15:50:29Z)
• In Depth We Trust: Reliable Monocular Depth Supervision for Gaussian Splatting [22.674046124865196]
  We introduce a training framework integrating scale-ambiguous and noisy depth priors into geometric supervision.<n>Experiments across diverse datasets show consistent improvements in geometric accuracy.
  arXiv  Detail & Related papers  (2026-04-07T11:15:15Z)
• 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)
• JointSplat: Probabilistic Joint Flow-Depth Optimization for Sparse-View Gaussian Splatting [10.690965024885358]
  Reconstructing 3D scenes from sparse viewpoints is a long-standing challenge with wide applications.<n>Recent advances in feed-forward 3D Gaussian sparse-view reconstruction methods provide an efficient solution for real-time novel view synthesis.<n>We propose JointSplat, a unified framework that leverages the complementarity between optical flow and depth.
  arXiv  Detail & Related papers  (2025-06-04T12:04:40Z)
• Refinement of Monocular Depth Maps via Multi-View Differentiable Rendering [6.372979654151044]
  Current state-of-the-art monocular depth estimators, trained on extensive datasets, generalize well but lack 3D consistency needed for many applications.<n>In this paper, we combine the strength of those generalizing monocular depth estimation techniques with multi-view data by framing this as an analysis-by-synthesis optimization problem.<n>Our method is able to generate detailed, high-quality, view consistent, accurate depth maps, also in challenging indoor scenarios, and outperforms state-of-the-art multi-view depth reconstruction approaches on such datasets.
  arXiv  Detail & Related papers  (2024-10-04T18:50:28Z)
• GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision [49.839374549646884]
  This paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception.<n>Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone.
  arXiv  Detail & Related papers  (2024-05-17T07:31:20Z)
• Self-Supervised Depth Completion Guided by 3D Perception and Geometry Consistency [17.68427514090938]
  This paper explores the utilization of 3D perceptual features and multi-view geometry consistency to devise a high-precision self-supervised depth completion method. Experiments on benchmark datasets of NYU-Depthv2 and VOID demonstrate that the proposed model achieves the state-of-the-art depth completion performance.
  arXiv  Detail & Related papers  (2023-12-23T14:19:56Z)
• FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models [67.96827539201071]
  We propose a novel test-time optimization approach for 3D scene reconstruction. Our method achieves state-of-the-art cross-dataset reconstruction on five zero-shot testing datasets.
  arXiv  Detail & Related papers  (2023-08-10T17:55:02Z)
• TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo [55.30992853477754]
  We present TANDEM, a real-time monocular tracking and dense framework. For pose estimation, TANDEM performs photometric bundle adjustment based on a sliding window of alignments. TANDEM shows state-of-the-art real-time 3D reconstruction performance.
  arXiv  Detail & Related papers  (2021-11-14T19:01:02Z)

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.