</> Code with Papers by Syntology

Papers › Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars

Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars

24 Aug 2020ECCV 2020 8arXiv:2008.10174archive 2025-07-28

Egor Zakharov, Aleksei Ivakhnenko, Aliaksandra Shysheya, Victor Lempitsky

We propose a neural rendering-based system that creates head avatars from a single photograph. Our approach models a person's appearance by decomposing it into two layers. The first layer is a pose-dependent coarse image that is synthesized by a small neural network. The second layer is defined by a pose-independent texture image that contains high-frequency details. The texture image is generated offline, warped and added to the coarse image to ensure a high effective resolution of synthesized head views. We compare our system to analogous state-of-the-art systems in terms of visual quality and speed. The experiments show significant inference speedup over previous neural head avatar models for a given visual quality. We also report on a real-time smartphone-based implementation of our system.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

saic-violet/bilayer-model officialmentioned on GitHubpytorchMPL-2.0 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Neural RenderingTalking Head Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Talking Head Generation VoxCeleb2 - 1-shot learning Fast Bi-layer Avatars (medium size) CSIM 0.653 #1 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning Fast Bi-layer Avatars (medium size) LPIPS 0.358 #1 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning Fast Bi-layer Avatars (medium size) Normalized Pose Error 43.3 #1 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning Fast Bi-layer Avatars (medium size) SSIM 0.508 #1 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning Fast Bi-layer Avatars (medium size) inference time (ms) 4 #1 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning First Order Motion Model (medium size) CSIM 0.638 #2 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning First Order Motion Model (medium size) LPIPS 0.311 #2 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning First Order Motion Model (medium size) Normalized Pose Error 47.8 #2 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning First Order Motion Model (medium size) SSIM 0.553 #2 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning First Order Motion Model (medium size) inference time (ms) 13 #2 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning Few-shot Vid-to-vid (medium size) CSIM 0.604 #3 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning Few-shot Vid-to-vid (medium size) LPIPS 0.368 #3 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning Few-shot Vid-to-vid (medium size) Normalized Pose Error 46.1 #3 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning Few-shot Vid-to-vid (medium size) SSIM 0.419 #3 of 5 Archive leaderboard report
Talking Head Generation VoxCeleb2 - 1-shot learning Few-shot Vid-to-vid (medium size) inference time (ms) 22 #3 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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