instant-ngp - 技术专题

A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.

A General NeRF Acceleration Toolbox in PyTorch.

Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code)

Easy NeRF synthetic dataset creation within Blender

"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024) - A Toolbox for CT reconstruction and X-ray Novel View Synthesis

INSTA - Instant Volumetric Head Avatars [CVPR2023]

"Neural Attenuation Fields for Sparse-View CBCT Reconstruction" (MICCAI 2022 Oral)

The official implementation of the paper Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields, the first interactive pixel-level NeRF editing tool.

INSTA - Instant Volumetric Head Avatars [Demo]

Nerf and extensions in all

[ECCV 2024] Pytorch code for our ECCV'24 paper NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields

Instant NeRF for depth/3d shape estimation of transparent objects

torch version of instant-ngp, image rendering

NeRF in NCNN with c++ & vulkan

🎉 [CVPR 2024] Pytorch implementation of 'Har Far Can We Compress Instant-NGP Based NeRF?'

JAX implementation of Instant-NGP (NeRF part)

Code for "Accurate Differential Operators for Hybrid Neural Fields", accepted at CVPR 2025

Dive into cutting-edge FusionSLAM, where SuperPoint, SuperGlue, Neural Depth Estimation, and Instant-NGP converge, elevating Monocular SLAM to unparalleled precision and performance. Redefining mapping, localization, and reconstruction in a single camera setup.

Pipeline for training multiple Instant-NGP NeRF model using transfer learning, and rendering dynamic scene based on your own view pose.

KoroKoro is an automated pipeline for converting 2D videos into detailed 3D models using advanced techniques, it uses a mix of advanced deep learning techniques to convert 30-second videos around an object to a fully interactive 3D object.