Descriptor-Free Multi-View Region Matching for Instance-Wise 3D Reconstruction

30/11/2020

Descriptor-Free Multi-View Region Matching for Instance-Wise 3D Reconstruction

Takuma Doi, Fumio Okura, Toshiki Nagahara, Yasuyuki Matsushita, Yasushi Yagi

Keywords:

Abstract Paper Similar Papers

Abstract: This paper proposes a multi-view extension of instance segmentation without relying on texture or shape descriptor matching. Multi-view instance segmentation becomes challenging for scenes with repetitive textures and shapes, e.g., plant leaves, due to the difficulty of multi-view matching using texture or shape descriptors. To this end, we propose a multi-view region matching method based on epipolar geometry, which does not rely on any feature descriptors. We further show that the epipolar region matching can be easily integrated into instance segmentation and effective for instance-wise 3D reconstruction. Experiments demonstrate the improved accuracy of multi-view instance matching and the 3D reconstruction compared to the baseline methods.

The video of this talk cannot be embedded. You can watch it here:

https://accv2020.github.io/miniconf/poster_301.html

(Link will open in new window)

0

0

0

0

Share

This is an embedded video. Talk and the respective paper are published at ACCV 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment

no comments yet

Similar Papers

17/08/2020

Cut-enhanced PolyCube-maps for feature-aware all-hex meshing

Hao-Xiang Guo, Xiaohan Liu, Dong-Ming Yan, Yang Liu

Keywords Paper

PolyCube-Map, cut-enhanced, feature-aware, hexahedral meshing

0

0

0

0

16:47

14/06/2020

PFCNN: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames

Yuqi Yang, Shilin Liu, Hao Pan and
Yang Liu, Xin Tong

Keywords Paper

surface meshes, convolution neural networks, parallel frames, translation equivariance, local euclidean structure, non-rigid shape, classification, segmentation, registration

0

0

0

0

0:58

14/06/2020

Towards High-Fidelity 3D Face Reconstruction From In-the-Wild Images Using Graph Convolutional Networks

Jiangke Lin, Yi Yuan, Tianjia Shao, Kun Zhou

Keywords Paper

3d face reconstruction, 3dmm, graph convolutional networks, texture, differentiable rendering

0

0

0

0

1:01

06/12/2020

Generative View Synthesis: From Single-view Semantics to Novel-view Images

Tewodros Amberbir Habtegebrial, Varun Jampani, Orazio Gallo, Didier Stricker

Keywords Paper

0

0

0

0

3:20

02/02/2021

Geodesic-HOF: 3D Reconstruction Without Cutting Corners

Ziyun Wang, Eric A. Mitchell, Volkan Isler, Daniel D. Lee

Keywords Paper

0

0

0

0

19:26

17/08/2020

Uncertainty quantification for multi-scan registration

Xiangru Huang, Zhenxiao Liang, Qixing Huang

Keywords Paper

multi-scan registration, uncertainty quantification, approximation error, view planning

0

0

0

0

21:04

06/12/2021

Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis

Tianchang Shen, Jun Gao, Kangxue Yin and
Ming-Yu Liu, Sanja Fidler

Keywords Paper

deep learning, optimization, generative model

0

0

0

0

14:32

22/11/2021

Two Heads are Better than One: Geometric-Latent Attention for Point Cloud Classification and Segmentation

Hanz Cuevas, Antonio-Javier Gallego, Robert B Fisher

Keywords Paper

point cloud, point cloud segmentation, 3D, point cloud classification, shape classification, deep 3D segmentation, deep learning, scene understanding, 3D scene understanding, light network, local agregation, gnn

0

0

0

0

2:57

05/01/2021

Novel View Synthesis via Depth-Guided Skip Connections

Yuxin Hou, Arno Solin, Juho Kannala

Keywords Paper

0

0

0

0

4:34

14/06/2020

Mesh-Guided Multi-View Stereo With Pyramid Architecture

Yuesong Wang, Tao Guan, Zhuo Chen and
Yawei Luo, Keyang Luo, Lili Ju

Keywords Paper

multi-view stereo, mesh-guided, depth map, pyramid architecture

0

0

0

0

1:01

06/12/2021

A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis

Xingang Pan, Xudong XU, Chen Change Loy and
Christian Theobalt, Bo Dai

Keywords Paper

generative model

0

0

0

0

11:15

30/11/2020

D2D: Keypoint Extraction with Describe to Detect Approach

Yurun Tian, Vassileios Balntas, Tony Ng and
Axel Barroso-Laguna, Yiannis Demiris, Krystian Mikolajczyk

Keywords Paper

0

0

0

0

4:34

14/06/2020

Learning Texture Transformer Network for Image Super-Resolution

Fuzhi Yang, Huan Yang, Jianlong Fu and
Hongtao Lu, Baining Guo

Keywords Paper

super-resolution, reference, image enhancement

0

0

0

0

1:01

22/11/2021

Learned Regularizers and Geometry for Image Denoising

Stacey E Levine, Ryan M Cecil, Marcelo Bertalmío

Keywords Paper

model based learning, partial differential equations, image geometry, level line curvature, image denoising

0

0

0

0

9:33

06/12/2021

Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects

Denys Rozumnyi, Martin R. Oswald, Vittorio Ferrari, Marc Pollefeys

Keywords Paper

optimization

0

0

0

0

10:44

14/06/2020

Deep 3D Capture: Geometry and Reflectance From Sparse Multi-View Images

Sai Bi, Zexiang Xu, Kalyan Sunkavalli and
David Kriegman, Ravi Ramamoorthi

Keywords Paper

appearance acquisition, 3d reconstruction, multi-view stereo

0

0

0

0

1:01

06/12/2021

OctField: Hierarchical Implicit Functions for 3D Modeling

Jia-Heng Tang, Weikai Chen, jie Yang and
Bo Wang, Songrun Liu, Bo Yang, Lin Gao

Keywords Paper

0

0

0

0

13:25

14/06/2020

End-to-End Optimization of Scene Layout

Andrew Luo, Zhoutong Zhang, Jiajun Wu, Joshua B. Tenenbaum

Keywords Paper

scene graph, scene synthesis, differentiable rendering, object layout, deep learning

0

0

0

0

4:58

17/08/2020

Deep geometric texture synthesis

Amir Hertz, Rana Hanocka, Raja Giryes, Daniel Cohen-Or

Keywords Paper

surface reconstruction, shape analysis, geometric deep learning

0

0

0

0

16:08

03/05/2021

Graph Convolution with Low-rank Learnable Local Filters

Xiuyuan Cheng, Zichen Miao, Qiang Qiu

Keywords Paper

0

0

0

0

10:41

14/06/2020

Perspective Plane Program Induction From a Single Image

Yikai Li, Jiayuan Mao, Xiuming Zhang and
William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu

Keywords Paper

inverse graphics, program synthesis, image manipulation, camera pose estimation, repeated pattern detection, image inpainting, image extrapolation

0

0

0

0

1:01

14/06/2020

Joint Texture and Geometry Optimization for RGB-D Reconstruction

Yanping Fu, Qingan Yan, Jie Liao, Chunxia Xiao

Keywords Paper

rgb-d reconstruction, 3d reconstruction, texture optimization, geometry optimization, joint texture and geometry optimization

0

0

0

0

0:57

14/06/2020

Learning a Neural 3D Texture Space From 2D Exemplars

Philipp Henzler, Niloy J. Mitra, Tobias Ritschel

Keywords Paper

texture synthesis, neural texture, solid texturing, implicit representation

0

0

0

0

1:01

17/08/2020

Vid2Curve: Simultaneous camera motion estimation and thin structure reconstruction from an RGB video

Peng Wang, Lingjie Liu, Nenglun Chen and
Hung-Kuo Chu, Christian Theobalt, Wenping Wang

Keywords Paper

image-based reconstruction, delicate structure, curve reconstruction

0

0

0

0

3:49

30/11/2020

DeepVoxels++: Enhancing the Fidelity of Novel View Synthesis from 3D Voxel Embeddings

Tong He, John Collomosse, Hailin Jin, Stefano Soatto

Keywords Paper

0

0

0

0

7:47

06/12/2020

Swapping Autoencoder for Deep Image Manipulation

Taesung Park, Jun-Yan Zhu, Oliver Wang and
Jingwan Lu, Eli Shechtman, Alexei Efros, Richard Zhang

Keywords Paper

0

0

0

0

3:20

17/08/2020

A low-parametric rhombic microstructure family for irregular lattices

Davi Colli Tozoni, Jérémie Dumas, Zhongshi Jiang and
Julian Panetta, Daniele Panozzo, Denis Zorin

Keywords Paper

shape optimization, deformable objects, homogenization, additive fabrication, microstructures

0

0

0

0

18:42

14/06/2020

OccuSeg: Occupancy-Aware 3D Instance Segmentation

Lei Han, Tian Zheng, Lan Xu, Lu Fang

Keywords Paper

instance segmentation, multi-task learning, occupancy

0

0

0

0

1:02

14/06/2020

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

Yue Jiang, Dantong Ji, Zhizhong Han, Matthias Zwicker

Keywords Paper

differentiable rendering, signed distance field, image-based 3d reconstruction, 3d shape optimization, deep learning, inverse graphics

0

0

0

0

5:01

06/12/2021

Generative Occupancy Fields for 3D Surface-Aware Image Synthesis

Xudong XU, Xingang Pan, Dahua Lin, Bo Dai

Keywords Paper

generative model

0

0

0

0

6:47

06/12/2020

Learning Deformable Tetrahedral Meshes for 3D Reconstruction

Jun Gao, Wenzheng Chen, Tommy Xiang and
Alec Jacobson, Morgan McGuire, Sanja Fidler

Keywords Paper

Applications -> Computer Vision; Deep Learning -> CNN Architectures, Applications -> Body Pose, Face, and Gesture Analysis

0

0

0

0

3:22

02/02/2021

SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition

Chengwei Zhang, Yunlu Xu, Zhanzhan Cheng and
Shiliang Pu, Yi Niu, Fei Wu, Futai Zou

Keywords Paper

0

0

0

0

14:11

19/08/2021

A Sketch-Transformer Network for Face Photo-Sketch Synthesis

Mingrui Zhu, Changcheng Liang, Nannan Wang and
Xiaoyu Wang, Zhifeng Li, Xinbo Gao

Keywords Paper

Computer Vision, 2D and 3D Computer Vision, Biometrics, Face and Gesture Recognition

0

0

0

0

12:42

06/12/2021

Recognizing Vector Graphics without Rasterization

XINYANG JIANG, LU LIU, Caihua Shan and
Yifei Shen, Xuanyi Dong, Dongsheng Li

Keywords Paper

deep learning, machine learning, vision, graph learning

0

0

0

0

15:02

14/06/2020

TextureFusion: High-Quality Texture Acquisition for Real-Time RGB-D Scanning

Joo Ho Lee, Hyunho Ha, Yue Dong and
Xin Tong, Min H. Kim

Keywords Paper

rgbd imaging, real-time application, 3d reconstruction, real-time 3d scanning, volumetric surface reconstruction, texture mapping, spatially varying warping, image alignment, texture stitching, texture generation

0

0

0

0

4:56

26/04/2020

U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation

Junho Kim, Minjae Kim, Hyeonwoo Kang, Kwang Hee Lee

Keywords Paper

Image-to-Image Translation, Generative Attentional Networks, Adaptive Layer-Instance Normalization

0

0

1

1

5:08

14/06/2020

Novel View Synthesis of Dynamic Scenes With Globally Coherent Depths From a Monocular Camera

Jae Shin Yoon, Kihwan Kim, Orazio Gallo and
Hyun Soo Park, Jan Kautz

Keywords Paper

view synthesis, depth estimation, dynamic scene, depth fusion, globally coherent depth, monocular camera

0

0

0

0

1:00

14/06/2020

HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation From a Single Depth Map

Jameel Malik, Ibrahim Abdelaziz, Ahmed Elhayek and
Soshi Shimada, Sk Aziz Ali, Vladislav Golyanik, Christian Theobalt, Didier Stricker

Keywords Paper

3d computer vision, 3d pose, 3d shape, depth image, convolutional neural network, voxelized hand shape, hand surface, depth map synthesizers, weak supervision, shape registration

0

0

0

0

1:01

14/06/2020

PointRend: Image Segmentation As Rendering

Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick

Keywords Paper

instance segmentation, semantic segmentation, high-resolution, implicit function, rendering

0

0

0

0

4:59

02/02/2021

Patch-Wise Attention Network for Monocular Depth Estimation

Sihaeng Lee, Janghyeon Lee, Byungju Kim and
Eojindl Yi, Junmo Kim

Keywords Paper

0

0

0

0

14:15