Novel View Synthesis
Synthesize a target image with an arbitrary target camera pose from given source images and their camera poses.
( Image credit: Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence )
Leaderboards
| TREND | DATASET | BEST METHOD | PAPER TITLE | PAPER | CODE | COMPARE |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
Greatest papers with code
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
• bmild/nerf
• 
Our algorithm represents a scene using a fully-connected (non-convolutional) deep network, whose input is a single continuous 5D coordinate (spatial location $(x, y, z)$ and viewing direction $(\theta, \phi)$) and whose output is the volume density and view-dependent emitted radiance at that spatial location.
Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines
• Fyusion/LLFF
•
We present a practical and robust deep learning solution for capturing and rendering novel views of complex real world scenes for virtual exploration.
Stereo Magnification: Learning View Synthesis using Multiplane Images
• google/stereo-magnification
•
The view synthesis problem--generating novel views of a scene from known imagery--has garnered recent attention due in part to compelling applications in virtual and augmented reality.
HoloGAN: Unsupervised learning of 3D representations from natural images
ICCV 2019
• thunguyenphuoc/HoloGAN
•
This shows that HoloGAN is the first generative model that learns 3D representations from natural images in an entirely unsupervised manner.
Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
NeurIPS 2019
• vsitzmann/scene-representation-networks
• 
Unsupervised learning with generative models has the potential of discovering rich representations of 3D scenes.
Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
NeurIPS 2019
• vsitzmann/scene-representation-networks
•
Unsupervised learning with generative models has the potential of discovering rich representations of 3D scenes.
View Synthesis by Appearance Flow
• RenYurui/Global-Flow-Local-Attention
•
We address the problem of novel view synthesis: given an input image, synthesizing new images of the same object or scene observed from arbitrary viewpoints.
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.
DeepVoxels: Learning Persistent 3D Feature Embeddings
CVPR 2019
• vsitzmann/deepvoxels
•
In this work, we address the lack of 3D understanding of generative neural networks by introducing a persistent 3D feature embedding for view synthesis.
Transformable Bottleneck Networks
ICCV 2019
• kyleolsz/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).