# YudongGuo/AD-NeRF

This repository contains a PyTorch implementation of "AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis".

Repository: https://github.com/YudongGuo/AD-NeRF
Canonical: https://ross.abutalabs.com/products/ad-nerf
Language: Python
License: MIT
License Family: permissive
Last push: 2023-10-27T11:05:12+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1896, "days_push": 1041, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1072, forks 177 (observed 2026-08-28T04:03:28.348758+00:00)

## What it is
A PyTorch implementation of AD-NeRF, an ICCV 2021 paper that synthesizes talking-head videos by driving neural radiance fields with audio input. It trains head and torso NeRFs from a portrait video and renders novel talking-head animations from arbitrary audio files.

## Use cases
- generate a talking head video from audio
- animate a portrait photo or video with speech audio
- reconstruct a person's head and torso as a neural radiance field
- drive a target person's face with another person's audio
- research audio-driven neural rendering for talking head synthesis

## When to choose
- you need research-grade audio-driven NeRF talking head synthesis
- you want to reproduce or build on the ICCV 2021 AD-NeRF paper
- you have a portrait video with voice audio and a GPU to train head and torso NeRFs

## When to avoid
- you need fast real-time talking head generation
- you lack a GPU or the patience for per-identity NeRF training
- you want a production-ready application with a simple UI rather than research code

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, audio-processing, video-processing, graphics, simulation
- domain: deep-learning, computer-vision, artificial-intelligence
- platform: python
- tags: nerf, talking-head, audio-driven, neural-radiance-fields, face-synthesis, pytorch, research-code, iccv-2021, audio, video, linux, gpu

## Member repositories
- YudongGuo/AD-NeRF (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:28.348758+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:53:40.438377+00:00, confidence not recorded.
  - readme: https://github.com/YudongGuo/AD-NeRF (fetched 2026-08-28T04:03:28.348758+00:00, sha 8b7654b03024)
- Data as of 2026-08-30T08:39:29.467469+00:00.