PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems

• URL: http://arxiv.org/abs/2604.16540v1
• Date: Fri, 17 Apr 2026 00:48:12 GMT
• Title: PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems
• Abstract summary: Poisoning input views of 3D reconstruction systems has been recently studied.<n>We propose PoInit-of-View, which optimize adversarial perturbations to intentionally introduce cross-view inconsistencies.<n> Experimental results demonstrate the effectiveness of our PoInit-of-View on diverse 3D reconstruction systems and datasets.
• Score: 55.84012796735184
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Poisoning input views of 3D reconstruction systems has been recently studied. However, we identify that existing studies simply backpropagate adversarial gradients through the 3D reconstruction pipeline as a whole, without uncovering the new vulnerability rooted in specific modules of the 3D reconstruction pipeline. In this paper, we argue that the structure-from-motion (SfM) initialization, as the geometric core of many widely used reconstruction systems, can be targeted to achieve transferable poisoning effects across diverse 3D reconstruction systems. To this end, we propose PoInit-of-View, which optimizes adversarial perturbations to intentionally introduce cross-view gradient inconsistencies at projections of corresponding 3D points. These inconsistencies disrupt keypoint detection and feature matching, thereby corrupting pose estimation and triangulation within SfM, eventually resulting in low-quality rendered views. We also provide a theoretical analysis that connects cross-view inconsistency to correspondence collapse. Experimental results demonstrate the effectiveness of our PoInit-of-View on diverse 3D reconstruction systems and datasets, surpassing the single-view baseline by 25.1% in PSNR and 16.5% in SSIM in black-box transfer settings, such as 3DGS to NeRF.

Related papers

• The Turning Point of 3D Plant Phenotyping: 3D Foundation Models Enable Minute-to-Second Cross-Crop Reconstruction and Beyond [24.45425568959962]
  We present one of the first cross-crop 3D phenotyping frameworks powered by 3DFMs.<n>We show that 3D Foundation Models reduce the average reconstruction time from 6.52 minutes to 1.58 seconds.
  arXiv  Detail & Related papers  (2026-07-02T06:10:54Z)
• Pano3D: Unified 3D Reconstruction and Panoptic Segmentation [68.18993232814061]
  We introduce an approach that performs 3D reconstruction and 3D panoptic segmentation in a unified framework.<n>We build on existing 3D reconstruction models and augment them with a set-based mask decoder.<n>Our method achieves state-of-the-art performance in 3D panoptic segmentation across ScanNet, ScanNet200, and ScanNet++ datasets.
  arXiv  Detail & Related papers  (2026-06-12T09:43:13Z)
• GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction [28.535167559081852]
  3D Gaussian Splatting (3DGS) has emerged as a prominent paradigm for 3D reconstruction and novel view synthesis.<n>We propose GeoQuery, a geometry-guided diffusion framework that integrates generative priors with explicit geometric cues.<n>GeoQuery can be seamlessly integrated into existing diffusion-based pipelines, enabling robust reconstruction even under extreme view sparsity.
  arXiv  Detail & Related papers  (2026-05-12T17:00:47Z)
• 3D Gaussian Splatting for Annular Dark Field Scanning Transmission Electron Microscopy Tomography Reconstruction [13.051560405222775]
  ADF-STEM tomography reconstructs nanoscale materials in 3D by integrating multi-view tilt-series images.<n>We introduce a coefficient $$ to stabilize scattering across tilt angles, ensuring consistent denza via scattering view normalization.<n>Experiments on 45-view and 15-view tilt series show that DenZa-Gaussian produces high-fidelity reconstructions and 2D projections that align more closely with original tilts.
  arXiv  Detail & Related papers  (2026-04-06T14:01:43Z)
• Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations [98.66466590444553]
  We propose Reliev3R, a weakly-supervised paradigm for training FFRMs from scratch without cost-prohibitive multi-view geometric annotations.<n>At the core of Reliev3R, we design an ambiguity-aware relative depth loss and a trigonometry-based reprojection loss to facilitate supervision for multi-view geometric consistency.
  arXiv  Detail & Related papers  (2026-04-01T06:46:54Z)
• ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation [28.308731720451053]
  We propose ReconViaGen to integrate reconstruction priors into the generative framework.<n>Our experiments demonstrate that our ReconViaGen can reconstruct complete and accurate 3D models consistent with input views in both global structure and local details.
  arXiv  Detail & Related papers  (2025-10-27T13:15:06Z)
• HBSplat: Robust Sparse-View Gaussian Reconstruction with Hybrid-Loss Guided Depth and Bidirectional Warping [11.035994094874141]
  HBSplat is a framework that seamlessly integrates robust structural cues, virtual view constraints, and occluded region completion.<n> HBSplat sets a new state-of-the-art, achieving up to 21.13 dB PSNR and 0.189 LPIPS, while maintaining real-time inference.
  arXiv  Detail & Related papers  (2025-09-29T15:03:31Z)
• T-3DGS: Removing Transient Objects for 3D Scene Reconstruction [83.05271859398779]
  Transient objects in video sequences can significantly degrade the quality of 3D scene reconstructions.<n>We propose T-3DGS, a novel framework that robustly filters out transient distractors during 3D reconstruction using Gaussian Splatting.
  arXiv  Detail & Related papers  (2024-11-29T07:45:24Z)
• Improving Neural Indoor Surface Reconstruction with Mask-Guided Adaptive Consistency Constraints [0.6749750044497732]
  We propose a two-stage training process, decouple view-dependent and view-independent colors, and leverage two novel consistency constraints to enhance detail reconstruction performance without requiring extra priors. Experiments on synthetic and real-world datasets show the capability of reducing the interference from prior estimation errors.
  arXiv  Detail & Related papers  (2023-09-18T13:05:23Z)
• Single-view 3D Mesh Reconstruction for Seen and Unseen Categories [69.29406107513621]
  Single-view 3D Mesh Reconstruction is a fundamental computer vision task that aims at recovering 3D shapes from single-view RGB images. This paper tackles Single-view 3D Mesh Reconstruction, to study the model generalization on unseen categories. We propose an end-to-end two-stage network, GenMesh, to break the category boundaries in reconstruction.
  arXiv  Detail & Related papers  (2022-08-04T14:13:35Z)
• NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction [64.36535692191343]
  Implicit neural representations have shown compelling results in offline 3D reconstruction and also recently demonstrated the potential for online SLAM systems. This paper addresses two key challenges: 1) seeking a criterion to measure the quality of the candidate viewpoints for the view planning based on the new representations, and 2) learning the criterion from data that can generalize to different scenes instead of hand-crafting one. Our method demonstrates significant improvements on various metrics for the rendered image quality and the geometry quality of the reconstructed 3D models when compared with variants using TSDF or reconstruction without view planning.
  arXiv  Detail & Related papers  (2022-07-22T10:05:36Z)
• Optical Diffraction Tomography based on 3D Physics-Inspired Neural Network (PINN) [0.1310865248866973]
  Optical diffraction tomography (ODT) is an emerging 3D imaging technique that is used for the 3D reconstruction of the refractive index (RI) for semi-transparent samples. Various inverse models have been proposed to reconstruct the 3D RI based on the holographic detection of different samples such as the Born and the Rytov approximations. We propose a different approach where a 3D neural network (NN) is employed. The NN is trained with a cost function derived from a physical model based on the physics of optical wave propagation.
  arXiv  Detail & Related papers  (2022-06-10T17:19:04Z)

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.