Browse > Computer Vision > Novel View Synthesis

Novel View Synthesis

7 papers with code · Computer Vision

Synthesize a target image with an arbitrary target camera pose from given source images and their camera poses.

State-of-the-art leaderboards

Greatest papers with code

Deferred Neural Rendering: Image Synthesis using Neural Textures

28 Apr 2019ondyari/FaceForensics

Similar to traditional textures, neural textures are stored as maps on top of 3D mesh proxies; however, the high-dimensional feature maps contain significantly more information, which can be interpreted by our new deferred neural rendering pipeline.

IMAGE GENERATION NOVEL VIEW SYNTHESIS

Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines

2 May 2019Fyusion/LLFF

We present a practical and robust deep learning solution for capturing and rendering novel views of complex real world scenes for virtual exploration.

NOVEL VIEW SYNTHESIS

Multi-view to Novel view: Synthesizing Novel Views with Self-Learned Confidence

Proceedings of the 15th European Conference on Computer Vision, 2018 shaohua0116/Multiview2Novelview

We address the task of multi-view novel view synthesis, where we are interested in synthesizing a target image with an arbitrary camera pose from given source images.

NOVEL VIEW SYNTHESIS

Transformable Bottleneck Networks

13 Apr 2019kyleolsz/TB-Networks

We propose a novel approach to performing fine-grained 3D manipulation of image content via a convolutional neural network, which we call the Transformable Bottleneck Network (TBN).

3D RECONSTRUCTION NOVEL VIEW SYNTHESIS

Monocular Neural Image Based Rendering with Continuous View Control

7 Jan 2019jcshim/sh

The approach is self-supervised and only requires 2D images and associated view transforms for training.

NOVEL VIEW SYNTHESIS

Cross-Domain 3D Equivariant Image Embeddings

6 Dec 2018machc/spherical_embeddings

This embedding encodes images with 3D shape properties and is equivariant to 3D rotations of the observed object.

NOVEL VIEW SYNTHESIS POSE ESTIMATION

HoloGAN: Unsupervised learning of 3D representations from natural images

2 Apr 2019christopher-beckham/hologan-pytorch

This shows that HoloGAN is the first generative model that learns 3D representations from natural images in an entirely unsupervised manner.

NOVEL VIEW SYNTHESIS