Embed human pose information into neural radiance fields (NeRF) to render images of humans in desired poses 🏃 from novel views
-
Updated
Sep 24, 2020 - Python
Embed human pose information into neural radiance fields (NeRF) to render images of humans in desired poses 🏃 from novel views
NeRF Meta-Learning with PyTorch
Implementation of the algorithms in the research paper iNeRF
Neural Radiance Fields
Using Fourier Feature Embedding within Neural Radiance Fields on Procedural Noise Functions tasks with focus on Perlin Noise.
Repository used to generate synthetic dataset from Kubric, used in "CoNeRF: Controllable Neural Radiance Fields"
Unofficial & improved implementation of NeRF--: Neural Radiance Fields Without Known Camera Parameters
[ICCV 2021 Oral] NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
A collection of NeRF extensions for fun and experimentation.
[CVPR 2022] "Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations" by Tianlong Chen*, Peihao Wang*, Zhiwen Fan, Zhangyang Wang
[ECCV 2022] "SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image", Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Humphrey Shi, Zhangyang Wang
Direct-PoseNet: Absolute Pose Regression with Photometric Consistency (3DV 2021)
Code implementation for NeRF and DietNeRF papers. NeRF presents a method for synthesizing novel views of complex 3D scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views.
NeRF implementation with minimal code and maximal readability using PyTorch
[ECCV 2022] RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering
[ECCV2022]"Unified Implicit Neural Stylization" which proposes a unified stylization framework for SIREN, SDF and NeRF
NeRF for Outdoor Scene Relighting [ECCV 2022]
Code release for my thesis 'Neural Rendering for Dynamic Urban Scenes'. We use Neural Radiance Fields to perform novel-view-synthesis in unbounded outdoor scenes and jointly regress 3D bounding box poses.
Reconstruction of a 3d scene from a set of images with different view points (camera in motion)
Add a description, image, and links to the neural-radiance-fields topic page so that developers can more easily learn about it.
To associate your repository with the neural-radiance-fields topic, visit your repo's landing page and select "manage topics."