Papers › Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis

Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis

18 Jul 2023ICCV 2023 1arXiv:2307.09323archive 2025-07-28

Jiahe Li, Jiawei Zhang, Xiao Bai, Jun Zhou, Lin Gu

This paper presents ER-NeRF, a novel conditional Neural Radiance Fields (NeRF) based architecture for talking portrait synthesis that can concurrently achieve fast convergence, real-time rendering, and state-of-the-art performance with small model size. Our idea is to explicitly exploit the unequal contribution of spatial regions to guide talking portrait modeling. Specifically, to improve the accuracy of dynamic head reconstruction, a compact and expressive NeRF-based Tri-Plane Hash Representation is introduced by pruning empty spatial regions with three planar hash encoders. For speech audio, we propose a Region Attention Module to generate region-aware condition feature via an attention mechanism. Different from existing methods that utilize an MLP-based encoder to learn the cross-modal relation implicitly, the attention mechanism builds an explicit connection between audio features and spatial regions to capture the priors of local motions. Moreover, a direct and fast Adaptive Pose Encoding is introduced to optimize the head-torso separation problem by mapping the complex transformation of the head pose into spatial coordinates. Extensive experiments demonstrate that our method renders better high-fidelity and audio-lips synchronized talking portrait videos, with realistic details and high efficiency compared to previous methods.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2307.09323")

Code

Syntology Ran 10 of 12 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 8 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

fictionarry/er-nerf officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 10 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
8ran
2unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from fictionarry/er-nerf. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

conv3x3 fictionarry/er-nerf/data_utils/face_parsing/resnet.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
create_layer_basic fictionarry/er-nerf/data_utils/face_parsing/resnet.py official repository ran MIT (permissive) · 325b8d54f52e2421 · report
get_audio_features fictionarry/er-nerf/nerf_triplane/utils.py official repository ran fingerprinted MIT (permissive) · 083a6ac840310b58 · report
linear_to_srgb fictionarry/er-nerf/nerf_triplane/utils.py official repository ran MIT (permissive) · df2164d2c1f74c1b · report
make_even_first_dim fictionarry/er-nerf/data_utils/hubert.py official repository ran fingerprinted MIT (permissive) · 5674b30130f49b38 · report
nerf_matrix_to_ngp fictionarry/er-nerf/nerf_triplane/provider.py official repository ran MIT (permissive) · cc5a245ddce1b228 · report
polygon_area fictionarry/er-nerf/nerf_triplane/provider.py official repository ran fingerprinted MIT (permissive) · 5e3067f7bf8c9e33 · report
sample_pdf fictionarry/er-nerf/nerf_triplane/renderer.py official repository ran · our draft was wrong MIT (permissive) · 8ed7b9fc7f33d1dd · report
smooth_camera_path fictionarry/er-nerf/nerf_triplane/provider.py official repository ran MIT (permissive) · c08d25b3e8575c34 · report
srgb_to_linear fictionarry/er-nerf/nerf_triplane/utils.py official repository ran MIT (permissive) · 78534c794e6d4ae8 · report
get_encoder fictionarry/er-nerf/encoding.py official repository unverified MIT (permissive) · c772127017598c32 · report
save_transforms fictionarry/er-nerf/data_utils/process.py official repository unverified MIT (permissive) · 874fee02f29df197 · report

Tasks

NeRF

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Pruning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections