3D Reconstruction

196 papers with code • 6 benchmarks • 24 datasets

Image: Gwak et al

Latest papers without code

Traffic4D: Single View Reconstruction of Repetitious Activity Using Longitudinal Self-Supervision

IEEE Intelligent Vehicles Symposium 2021

Reconstructing 4D vehicular activity (3D space and time) from cameras is useful for autonomous vehicles, commuters and local authorities to plan for smarter and safer cities.

3D Reconstruction Anomaly Detection +1

Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking

19 Jun 2021

This paper introduces an approach for multi-human 3D pose estimation and tracking based on calibrated multi-view.

3D Multi-Person Pose Estimation 3D Pose Estimation +1

Learning Compositional Shape Priors for Few-Shot 3D Reconstruction

11 Jun 2021

The impressive performance of deep convolutional neural networks in single-view 3D reconstruction suggests that these models perform non-trivial reasoning about the 3D structure of the output space.

3D Reconstruction Few-Shot Learning +1

Mirror3D: Depth Refinement for Mirror Surfaces

11 Jun 2021

Despite recent progress in depth sensing and 3D reconstruction, mirror surfaces are a significant source of errors.

3D Reconstruction Depth Estimation

Shape As Points: A Differentiable Poisson Solver

7 Jun 2021

However, the implicit nature of neural implicit representations results in slow inference time and requires careful initialization.

3D Reconstruction

Robotic Inspection and 3D GPR-based Reconstruction for Underground Utilities

3 Jun 2021

Ground Penetrating Radar (GPR) is an effective non-destructive evaluation (NDE) device for inspecting and surveying subsurface objects (i. e., rebars, utility pipes) in complex environments.

3D Reconstruction GPR

Reconstructing Small 3D Objects in front of a Textured Background

24 May 2021

It is a particular variation of multibody structure from motion, which specializes to two objects only.

3D Reconstruction Structure from Motion

Drone-based AI and 3D Reconstruction for Digital Twin Augmentation

20 May 2021

In this work, an Information Fusion framework is proposed to seamlessly fuse heterogeneous components in a Digital Twin framework from the variety of technologies involved.

3D Reconstruction Defect Detection

StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects

17 May 2021

We present StrobeNet, a method for category-level 3D reconstruction of articulating objects from one or more unposed RGB images.

3D Reconstruction

Galois/monodromy groups for decomposing minimal problems in 3D reconstruction

10 May 2021

We consider three classical cases--3-point absolute pose, 5-point relative pose, and 4-point homography estimation for calibrated cameras--where the decomposition and symmetries may be naturally understood in terms of the Galois/monodromy group.

3D Reconstruction Homography Estimation +1