megvii-research/AAAI2023-PVD

[IJCV] Official Implementation of PVD and PVDAL: http://sk-fun.fun/PVD-AL/

45
/ 100
Emerging

This project helps researchers and developers working with 3D scene reconstruction improve the efficiency and compatibility of their Neural Radiance Fields (NeRF) models. It takes an existing NeRF model of one architecture type (like MLP, sparse tensors, or hash tables) and distills its knowledge into a more efficient or compatible NeRF model of a different architecture, producing a new, optimized 3D scene representation. This is for researchers and engineers developing advanced 3D vision systems.

181 stars.

Use this if you need to convert between different NeRF architectures to optimize for performance, memory, or specific deployment scenarios while maintaining high visual quality.

Not ideal if you are looking for an off-the-shelf 3D model viewer or a tool for casual 3D content creation without deep technical involvement in NeRF development.

3D reconstruction neural rendering computer vision research scene representation model optimization
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

181

Forks

5

Language

Python

License

MIT

Last pushed

Mar 17, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/megvii-research/AAAI2023-PVD"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.