Papers › Pixel Codec Avatars

Pixel Codec Avatars

9 Apr 2021CVPR 2021 1arXiv:2104.04638archive 2025-07-28

Shugao Ma, Tomas Simon, Jason Saragih, Dawei Wang, Yuecheng Li, Fernando de la Torre, Yaser Sheikh

Telecommunication with photorealistic avatars in virtual or augmented reality is a promising path for achieving authentic face-to-face communication in 3D over remote physical distances. In this work, we present the Pixel Codec Avatars (PiCA): a deep generative model of 3D human faces that achieves state of the art reconstruction performance while being computationally efficient and adaptive to the rendering conditions during execution. Our model combines two core ideas: (1) a fully convolutional architecture for decoding spatially varying features, and (2) a rendering-adaptive per-pixel decoder. Both techniques are integrated via a dense surface representation that is learned in a weakly-supervised manner from low-topology mesh tracking over training images. We demonstrate that PiCA improves reconstruction over existing techniques across testing expressions and views on persons of different gender and skin tone. Importantly, we show that the PiCA model is much smaller than the state-of-art baseline model, and makes multi-person telecommunicaiton possible: on a single Oculus Quest 2 mobile VR headset, 5 avatars are rendered in realtime in the same scene.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 11 ran (of which 11 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 11 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 15 samples from 1 repository, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

facebookresearch/multiface mentioned on GitHubpytorchSyntology: 15 samples, 11 ran (0 instrument-failed) · 4 unverified 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

15 samples harvested: 11 ran (of which 11 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 11 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

11ran
4unverified

Licence: 15 of the 15 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 facebookresearch/multiface. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 6 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

facebookresearch/multiface community (archive-listed) 15 samples, 11 ran (0 instrument-failed) · 4 unverified
ColorCorrection models.py ran licence not identified · pointer only · a9fcaa9469dd1d91 · report fixture: returned ColorCorrection · level recorded 2026-09-22
Conv2dWN models.py ran fingerprinted licence not identified · pointer only · 50a5166ad6333613 · report fixture: returned Conv2dWN · level recorded 2026-09-22
Conv2dWNUB models.py ran licence not identified · pointer only · 7e12c575b85ada25 · report fixture: returned Conv2dWNUB · level recorded 2026-09-22
ConvDownsample models.py ran fingerprinted licence not identified · pointer only · 6e5e8a434395b6fd · report fixture: returned ConvDownsample · level recorded 2026-09-22
ConvTranspose2dWN models.py ran fingerprinted licence not identified · pointer only · 53aef6225f594b6c · report fixture: returned ConvTranspose2dWN · level recorded 2026-09-22
ConvTranspose2dWNUB models.py ran licence not identified · pointer only · f44b8aeb0c500018 · report fixture: returned ConvTranspose2dWNUB · level recorded 2026-09-22
ConvUpsample models.py ran licence not identified · pointer only · b03b8397f508bf0a · report fixture: returned ConvUpsample · level recorded 2026-09-22
DeconvTexelBias models.py ran licence not identified · pointer only · 5c61f272cf598f2a · report fixture: returned DeconvTexelBias · level recorded 2026-09-22
LinearWN models.py ran licence not identified · pointer only · b8078040c9685a98 · report fixture: returned LinearWN · level recorded 2026-09-22
TextureDecoder models.py ran fingerprinted licence not identified · pointer only · c84f517ad3be341c · report fixture: returned TextureDecoder · level recorded 2026-09-22
TextureEncoder models.py ran licence not identified · pointer only · 2c7281eb2419dd6d · report fixture: returned TextureEncoder · level recorded 2026-09-22
DeepAppearanceDecoder models.py unverified licence not identified · pointer only · 20d6ee1dbee7d492 · report
DeepAppearanceVAE models.py unverified licence not identified · pointer only · ade4a68dffee59fc · report
DeepApperanceEncoder models.py unverified licence not identified · pointer only · 237b5ff09c06871c · report
glorot in 26 papers models.py unverified licence not identified · pointer only · 0f6bb5f67673c772 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Pixel Codec Avatars (graph method: Pixel Codec Avatars). 15 bricks; individually on a fixture: 11 ran (of which 11 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 11 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. DeepAppearanceVAE entry · level 0 · unverified · ade4a68dffee59fc
  2. ColorCorrection helper · level 1 · ran · a9fcaa9469dd1d91
  3. DeepAppearanceDecoder helper · level 0 · unverified · 20d6ee1dbee7d492
  4. DeepApperanceEncoder helper · level 0 · unverified · 237b5ff09c06871c
  5. LinearWN helper · level 1 · ran · b8078040c9685a98
  6. TextureDecoder helper · level 1 · ran · c84f517ad3be341c
  7. glorot helper · level 0 · unverified · 0f6bb5f67673c772
  8. TextureEncoder helper · level 1 · ran · 2c7281eb2419dd6d
  9. ConvUpsample helper · level 1 · ran · b03b8397f508bf0a
  10. Conv2dWN helper · level 1 · ran · 50a5166ad6333613
  11. Conv2dWNUB helper · level 1 · ran · 7e12c575b85ada25
  12. ConvTranspose2dWN helper · level 1 · ran · 53aef6225f594b6c
  13. ConvTranspose2dWNUB helper · level 1 · ran · f44b8aeb0c500018
  14. ConvDownsample helper · level 1 · ran · 6e5e8a434395b6fd
  15. DeconvTexelBias helper · level 1 · ran · 5c61f272cf598f2a

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2104.04638") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Decoder

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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