computer-vision-11

Multi-View 3D Reconstruction

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in multi-view-3d-reconstruction-11

Trend

Dataset

Best Model

Actions

ETH3D

Libraries

i

Use these libraries to find multi-view-3d-reconstruction-11 models and implementations

Datasets

ETH3D

Synthetic Soccer NeRF Dataset

Subtasks

No subtasks available.

Most implemented papers

Pix2Vox: Context-Aware 3D Reconstruction From Single and Multi-View Images

Shengping Zhang, Shangchen Zhou, Haozhe Xie, H. Yao, Xiaoshuai Sun, Xiaojun Tong•Wed Jan 30 2019

Experimental results on the ShapeNet and Pix3D benchmarks indicate that the proposed Pix2Vox outperforms state-of-the-arts by a large margin, and the proposed method is 24 times faster than 3D-R2N2 in terms of backward inference time.

364

Content

0

Paper Graph

Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction

Bo Yang, A. Markham, Sen Wang, Niki Trigoni•Wed Aug 01 2018

A new feed-forward neural module, named AttSets, together with a dedicated training algorithm, named FASet, to attentively aggregate an arbitrarily sized deep feature set for multi-view 3D reconstruction, which significantly outperforms existing aggregation approaches.

146 0

Paper Graph

SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization

Matthias Zwicker, Zhizhong Han, Yue Jiang, Dantong Ji•Sat Dec 14 2019

It is demonstrated that the proposed SDFDiff, a novel approach for image-based shape optimization using differentiable rendering of 3D shapes represented by signed distance functions, can be integrated with deep learning models, which opens up options for learning approaches on 3D objects without 3D supervision.

253 0

Paper Graph

Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision

Andreas Geiger, L. Mescheder, Michael Oechsle, Michael Niemeyer•Sun Dec 15 2019

This work proposes a differentiable rendering formulation for implicit shape and texture representations, showing that depth gradients can be derived analytically using the concept of implicit differentiation, and finds that this method can be used for multi-view 3D reconstruction, directly resulting in watertight meshes.

1074 0

Paper Graph

Planar Prior Assisted PatchMatch Multi-View Stereo

Wenbing Tao, Qingshan Xu•Wed Dec 25 2019

A probabilistic graphical model is utilized to embed planar models into PatchMatch multi-view stereo and contribute a novel multi- view aggregated matching cost that takes both photometric consistency and planar compatibility into consideration, making it suited for the depth estimation of both non-planar and planars regions.

149 0

Paper Graph

Multi-view 3D Reconstruction of a Texture-less Smooth Surface of Unknown Generic Reflectance

Hongdong Li, Yinqiang Zheng, Imari Sato, Ziang Cheng, Yuta Asano•Mon May 24 2021

This paper proposes a simple and practical solution to overcome the challenge of establishing cross-view correspondences where photometric constancy is violated based on a co-located camera-light scanner device and develops an optimization algorithm that robustly recovers globally optimal shape and reflectance even from a random initialization.

26 0

Paper Graph

Extremely Dense Point Correspondences Using a Learned Feature Descriptor

Gregory Hager, M. Ishii, M. Unberath, R. Taylor, Xingtong Liu, Yiping Zheng, Benjamin Killeen•Sun Mar 01 2020

This work presents an effective self-supervised training scheme and novel loss design for dense descriptor learning and demonstrates that the proposed dense descriptor can generalize to unseen patients and scopes, thereby largely improving the performance of Structure from Motion (SfM) in terms of model density and completeness.

48 0

Paper Graph

H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction

F. Moreno-Noguer, Xavier Giró-i-Nieto, Albert Pumarola, Eduard Ramon, G. Triginer, Janna Escur, Jaime García•Mon Jul 26 2021

This paper endows coordinate-based representations with a probabilistic shape prior that enables faster convergence and better generalization when using few input images, and achieves high-fidelity head reconstructions with a high level of detail that consistently outperforms both state-of-the-art 3D Morphable Models methods in the few-shot scenario, and nonparametric methods when large sets of views are available.

104 0

Paper Graph

LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction

Federico Tombari, Farid Yagubbayli, A. Tonioni•Tue Jun 22 2021

LegoFormer is proposed, a transformer model for voxel-based 3D reconstruction that uses the attention layers to share information among views during all computational stages, and to parametrize the output with a series of low-rank decomposition factors.

40 0

Paper Graph

3D-RETR: End-to-End Single and Multi-View 3D Reconstruction with Transformers

Z. Shi, Zhao Meng, Yiran Xing, Yunpu Ma, R. Wattenhofer•Sat Oct 16 2021

3D-RETR is proposed, which is able to perform end-to-end 3D REconstruction with TRansformers, and is capable of 3D reconstruction from a single view or multiple views.

38 0

Paper Graph

Adding a benchmark result helps the community track progress.