paper-with-me

홈 › Papers

Constructing Canonical Regions for Fast and Effective View Selection

2016-06-01 · CVPR 2016 6 · Wencheng Wang, Tianhao Gao

In view selection, little work has been done for optimizing the search process; views must be densely distributed and checked individually. Thus, evaluating poor views wastes much time, and a poor view may even be misidentified as a best one. In this paper, we propose a search strategy by identifying the regions that are very likely to contain best views, referred to as canonical regions. It is by decomposing the model under investigation into meaningful parts, and using the canonical views of these parts to generate canonical regions. Applying existing view selection methods in the canonical regions can not only accelerate the search process but also guarantee the quality of obtained views. As a result, when our canonical regions are used for searching N-best views during comprehensive model analysis, we can attain greater search speed and reduce the number of views required. Experimental results show the effectiveness of our method.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors

2026-03-18 · Aymen Mir, Riza Alp Guler, Xiangjun Tang, Peter Wonka 외 arxiv

We present AHOY, a method for reconstructing complete, animatable 3D Gaussian avatars from in-the-wild monocular video despite heavy occlusion. Existing methods assume unoccluded input-a fully visible subject, often in a…

Shock-Aware Physics-Guided Fusion-DeepONet Operator for Rarefied Micro-Nozzle Flows

2025-10-18 · Ehsan Roohi, Amirmehran Mahdavi arxiv

We present a comprehensive, physics aware deep learning framework for constructing fast and accurate surrogate models of rarefied, shock containing micro nozzle flows. The framework integrates three key components, a Fus…

FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction

2025-01-01 · CVPR 2025 1 · Yifan Wang, Peishan Yang, Zhen Xu, Jiaming Sun 외

This paper addresses the challenge of reconstructing dynamic 3D scenes with complex motions. Some recent works define 3D Gaussian primitives in the canonical space and use deformation fields to map canonical primitiv…

FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction

2025-06-05 · Yifan Wang, Peishan Yang, Zhen Xu, Jiaming Sun 외

This paper addresses the challenge of reconstructing dynamic 3D scenes with complex motions. Some recent works define 3D Gaussian primitives in the canonical space and use deformation fields to map canonical primitives t…

ARCH++: Animation-Ready Clothed Human Reconstruction Revisited

2021-08-17 · ICCV 2021 10 · Tong He, Yuanlu Xu, Shunsuke Saito, Stefano Soatto 외

We present ARCH++, an image-based method to reconstruct 3D avatars with arbitrary clothing styles. Our reconstructed avatars are animation-ready and highly realistic, in both the visible regions from input views and the …

3D Object Reconstruction From A Single ImageImage-to-Image Translation