Browse > Computer Vision > 3D > 3D Reconstruction

3D Reconstruction

57 papers with code ยท Computer Vision
Subtask of 3D

State-of-the-art leaderboards

Latest papers without code

3D Instance Segmentation via Multi-task Metric Learning

20 Jun 2019

The second goal is to learn instance information by estimating directional information of the instances' centers of mass densely for each voxel.

3D INSTANCE SEGMENTATION 3D RECONSTRUCTION METRIC LEARNING MULTI-TASK LEARNING SEMANTIC SEGMENTATION

Learning to Reconstruct and Understand Indoor Scenes from Sparse Views

19 Jun 2019

This paper proposes a new method for simultaneous 3D reconstruction and semantic segmentation of indoor scenes.

3D RECONSTRUCTION DEPTH ESTIMATION SEMANTIC SEGMENTATION

Analytical Derivatives for Differentiable Renderer: 3D Pose Estimation by Silhouette Consistency

19 Jun 2019

The experimental results also show that the proposed differentiable renderer is of higher accuracy and efficiency compared with previous method of differentiable renderer.

3D POSE ESTIMATION 3D RECONSTRUCTION

Differentiable probabilistic models of scientific imaging with the Fourier slice theorem

18 Jun 2019

Finally, we demonstrate how the reconstruction algorithm can be extended with an amortized inference scheme on unknown attributes such as object pose.

3D RECONSTRUCTION POSE ESTIMATION

Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era

15 Jun 2019

Given this new era of rapid evolution, this article provides a comprehensive survey of the recent developments in this field.

3D OBJECT RECONSTRUCTION 3D RECONSTRUCTION

Single-Image Piece-Wise Planar 3D Reconstruction via Associative Embedding

CVPR 2019

In the first stage, we train a CNN to map each pixel to an embedding space where pixels from the same plane instance have similar embeddings.

3D RECONSTRUCTION INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters

CVPR 2019

Standard RGB-D trackers treat the target as a 2D structure, which makes modelling appearance changes related even to out-of-plane rotation challenging.

3D RECONSTRUCTION OBJECT TRACKING

DeepVoxels: Learning Persistent 3D Feature Embeddings

CVPR 2019

In this work, we address the lack of 3D understanding of generative neural networks by introducing a persistent 3D feature embedding for view synthesis.

3D RECONSTRUCTION NOVEL VIEW SYNTHESIS

Scan2CAD: Learning CAD Model Alignment in RGB-D Scans

CVPR 2019

For a 3D reconstruction of an indoor scene, our method takes as input a set of CAD models, and predicts a 9DoF pose that aligns each model to the underlying scan geometry.

3D RECONSTRUCTION