Browse > Computer Vision > 3D > 3D Reconstruction

3D Reconstruction

67 papers with code · Computer Vision
Subtask of 3D

State-of-the-art leaderboards

Latest papers with code

Self-Supervised Deep Depth Denoising

3 Sep 2019VCL3D/DeepDepthDenoising

Specifically, the proposed autoencoder exploits multiple views of the same scene from different points of view in order to learn to suppress noise in a self-supervised end-to-end manner using depth and color information during training, yet only depth during inference.

3D RECONSTRUCTION DENOISING

14
03 Sep 2019

Probabilistic Reconstruction Networks for 3D Shape Inference from a Single Image

20 Aug 2019Regenerator/prns

We study end-to-end learning strategies for 3D shape inference from images, in particular from a single image.

3D RECONSTRUCTION

1
20 Aug 2019

Point Cloud Super Resolution with Adversarial Residual Graph Networks

arXiv:1908.02111 2019 wuhuikai/PointCloudSuperResolution

The key idea of the proposed network is to exploit the local similarity of point cloud and the analogy between LR input and HR output.

3D RECONSTRUCTION POINT CLOUD SUPER RESOLUTION SUPER RESOLUTION

9
06 Aug 2019

PU-GAN: a Point Cloud Upsampling Adversarial Network

25 Jul 2019liruihui/PU-GAN

Point clouds acquired from range scans are often sparse, noisy, and non-uniform.

3D RECONSTRUCTION POINT CLOUD SUPER RESOLUTION

47
25 Jul 2019

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

CVPR 2019 mihaidusmanu/d2-net

In this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions.

3D RECONSTRUCTION

179
01 Jun 2019

Learning Non-Volumetric Depth Fusion Using Successive Reprojections

CVPR 2019 simon-donne/defusr

Given a set of input views, multi-view stereopsis techniques estimate depth maps to represent the 3D reconstruction of the scene; these are fused into a single, consistent, reconstruction -- most often a point cloud.

3D RECONSTRUCTION DEPTH ESTIMATION

30
01 Jun 2019

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

26 May 2019laughtervv/DISN

Combining global and local features significantly improves the accuracy of the predicted signed distance field.

3D RECONSTRUCTION SINGLE-VIEW 3D RECONSTRUCTION

48
26 May 2019

Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes

CVPR 2019 ziquan111/RobustPCLReconstruction

Furthermore, we show that by using a Gaussian-Uniform mixture model, our approach degenerates to the formulation of a state-of-the-art approach for robust indoor reconstruction.

3D RECONSTRUCTION

59
23 May 2019

Learning Perspective Undistortion of Portraits

18 May 2019bearjoy730/Learning-Perspective-Undistortion-of-Portraits

In contrast to the previous state-of-the-art approach, our method handles even portraits with extreme perspective distortion, as we avoid the inaccurate and error-prone step of first fitting a 3D face model.

3D RECONSTRUCTION CALIBRATION FACE RECOGNITION

11
18 May 2019

D2-Net: A Trainable CNN for Joint Detection and Description of Local Features

9 May 2019mihaidusmanu/d2-net

In this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions.

3D RECONSTRUCTION

179
09 May 2019