3D Reconstruction

534 papers with code • 8 benchmarks • 54 datasets

3D Reconstruction is the task of creating a 3D model or representation of an object or scene from 2D images or other data sources. The goal of 3D reconstruction is to create a virtual representation of an object or scene that can be used for a variety of purposes, such as visualization, animation, simulation, and analysis. It can be used in fields such as computer vision, robotics, and virtual reality.

Image: Gwak et al

GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering

ajhamdi/ges-splatting 15 Feb 2024

With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks while requiring less than half the memory storage of Gaussian Splatting and increasing the rendering speed by up to 39%.

144
15 Feb 2024

PC-NeRF: Parent-Child Neural Radiance Fields Using Sparse LiDAR Frames in Autonomous Driving Environments

biter0088/pc-nerf 14 Feb 2024

With extensive experiments, PC-NeRF is proven to achieve high-precision novel LiDAR view synthesis and 3D reconstruction in large-scale scenes.

139
14 Feb 2024

Camera Calibration through Geometric Constraints from Rotation and Projection Matrices

cvlablums/cvgl-camera-calibration 13 Feb 2024

The process of camera calibration involves estimating the intrinsic and extrinsic parameters, which are essential for accurately performing tasks such as 3D reconstruction, object tracking and augmented reality.

3
13 Feb 2024

EscherNet: A Generative Model for Scalable View Synthesis

kxhit/EscherNet 6 Feb 2024

We introduce EscherNet, a multi-view conditioned diffusion model for view synthesis.

141
06 Feb 2024

DeepAAT: Deep Automated Aerial Triangulation for Fast UAV-based Mapping

whu-usi3dv/deepaat 2 Feb 2024

The experimental results demonstrate DeepAAT's substantial improvements over conventional AAT methods, highlighting its potential in the efficiency and accuracy of UAV-based 3D reconstruction tasks.

36
02 Feb 2024

Local Feature Matching Using Deep Learning: A Survey

vignywang/awesome-local-feature-matching 31 Jan 2024

The objective of this endeavor is to furnish a comprehensive overview of local feature matching methods.

13
31 Jan 2024

OmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision

sbrunoberenguel/omniscv 30 Jan 2024

In this paper, we present a tool for generating datasets of omnidirectional images with semantic and depth information.

39
30 Jan 2024

3D Reconstruction and New View Synthesis of Indoor Environments based on a Dual Neural Radiance Field

pcl3dv/dunerf 26 Jan 2024

One of the innovative features of Du-NeRF is that it decouples a view-independent component from the density field and uses it as a label to supervise the learning process of the SDF field.

4
26 Jan 2024

pix2gestalt: Amodal Segmentation by Synthesizing Wholes

cvlab-columbia/pix2gestalt 25 Jan 2024

We introduce pix2gestalt, a framework for zero-shot amodal segmentation, which learns to estimate the shape and appearance of whole objects that are only partially visible behind occlusions.

60
25 Jan 2024

Range-Agnostic Multi-View Depth Estimation With Keyframe Selection

andreaconti/ramdepth 25 Jan 2024

Methods for 3D reconstruction from posed frames require prior knowledge about the scene metric range, usually to recover matching cues along the epipolar lines and narrow the search range.

33
25 Jan 2024