Search arXivSearch

arXiv · 2211.14822

Adjustable Method Based on Body Parts for Improving the Accuracy of 3D Reconstruction in Visually Important Body Parts from Silhouettes

Abstract

This research proposes a novel adjustable algorithm for reconstructing 3D body shapes from front and side silhouettes. Most recent silhouette-based approaches use a deep neural network trained by silhouettes and key points to estimate the shape parameters but cannot accurately fit the model to the body contours and consequently are struggling to cover detailed body geometry, especially in the torso. In addition, in most of these cases, body parts have the same accuracy priority, making the optimization harder and avoiding reaching the optimum possible result in essential body parts, like the torso, which is visually important in most applications, such as virtual garment fitting. In the proposed method, we can adjust the expected accuracy for each body part based on our purpose by assigning coefficients for the distance of each body part between the projected 3D body and 2D silhouettes. To measure this distance, we first recognize the correspondent body parts using body segmentation in both views. Then, we align individual body parts by 2D rigid registration and match them using pairwise matching. The objective function tries to minimize the distance cost for the individual body parts in both views based on distances and coefficients by optimizing the statistical model parameters. We also handle the slight variation in the degree of arms and limbs by matching the pose. We evaluate the proposed method with synthetic body meshes from the normalized S-SCAPE. The result shows that the algorithm can more accurately reconstruct visually important body parts with high coefficients.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Aref Hemati, Azam Bastanfard. 2022-11-27. Adjustable Method Based on Body Parts for Improving the Accuracy of 3D Reconstruction in Visually Important Body Parts from Silhouettes. https://arxiv.org/abs/2211.14822

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses

Deep Neural Networks (DNNs) have revolutionized various domains with their exceptional performance across numerous applications. However, Model Inversion (MI) attacks, which disclose private information about the training dataset by abusing access to the trained models, have emerged as a formidable privacy threat. Given a trained network, these attacks enable adversaries to reconstruct high-fidelity data that closely aligns with the private training samples, posing significant privacy concerns. Despite the rapid advances in the field, we lack a comprehensive and systematic overview of existing MI attacks and defenses. To fill this gap, this paper thoroughly investigates this realm and presents a holistic survey. Firstly, our work briefly reviews early MI studies on traditional machine learning scenarios. We then elaborately analyze and compare numerous recent attacks and defenses on Deep Neural Networks (DNNs) across multiple modalities and learning tasks. By meticulously analyzing their distinctive features, we summarize and classify these methods into different categories and provide a novel taxonomy. Finally, this paper discusses promising research directions and presents potential solutions to open issues. To facilitate further study on MI attacks and defenses, we have implemented an open-source model inversion toolbox on GitHub (https://github.com/ffhibnese/Model-Inversion-Attack-ToolBox).

cs.CV

ALINA: Advanced Line Identification and Notation Algorithm

Labels are the cornerstone of supervised machine learning algorithms. Most visual recognition methods are fully supervised, using bounding boxes or pixel-wise segmentations for object localization. Traditional labeling methods, such as crowd-sourcing, are prohibitive due to cost, data privacy, amount of time, and potential errors on large datasets. To address these issues, we propose a novel annotation framework, Advanced Line Identification and Notation Algorithm (ALINA), which can be used for labeling taxiway datasets that consist of different camera perspectives and variable weather attributes (sunny and cloudy). Additionally, the CIRCular threshoLd pixEl Discovery And Traversal (CIRCLEDAT) algorithm has been proposed, which is an integral step in determining the pixels corresponding to taxiway line markings. Once the pixels are identified, ALINA generates corresponding pixel coordinate annotations on the frame. Using this approach, 60,249 frames from the taxiway dataset, AssistTaxi have been labeled. To evaluate the performance, a context-based edge map (CBEM) set was generated manually based on edge features and connectivity. The detection rate after testing the annotated labels with the CBEM set was recorded as 98.45%, attesting its dependability and effectiveness.

cs.CV

DisasterInsight: A Building-Centric Benchmark for Evaluating Vision--Language Models in Disaster Response

Vision--language models (VLMs) show promise for disaster-response remote sensing, but existing benchmarks mainly emphasize scene-level or damage-centric assessment. To study this building-centric gap, we introduce \method{}, a diagnostic benchmark built on xBD, a pre/post-disaster satellite dataset with building-level damage labels. \method{} enriches building instances with OpenStreetMap-derived functional labels and contains 134{,}108 task-specific instruction records across 15 task types, spanning instance-level assessment, scene-level counting, multi-instance reasoning, and structured report generation. The benchmark supports RGB pre/post-disaster imagery, single- and multi-view instance formulations, and scene-level RGB/SAR diagnostic inputs. Experiments with general-domain and remote-sensing VLMs show that models perform better on visible damage cues than on building-function understanding, multi-instance reasoning, counting, and grounded reporting. Instruction tuning improves performance on several tasks but does not close this building-centric gap.

cs.CV