Papers › VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
YuChao Gu, Xintao Wang, Liangbin Xie, Chao Dong, Gen Li, Ying Shan, Ming-Ming Cheng
Although generative facial prior and geometric prior have recently demonstrated high-quality results for blind face restoration, producing fine-grained facial details faithful to inputs remains a challenging problem. Motivated by the classical dictionary-based methods and the recent vector quantization (VQ) technique, we propose a VQ-based face restoration method - VQFR. VQFR takes advantage of high-quality low-level feature banks extracted from high-quality faces and can thus help recover realistic facial details. However, the simple application of the VQ codebook cannot achieve good results with faithful details and identity preservation. Therefore, we further introduce two special network designs. 1). We first investigate the compression patch size in the VQ codebook and find that the VQ codebook designed with a proper compression patch size is crucial to balance the quality and fidelity. 2). To further fuse low-level features from inputs while not "contaminating" the realistic details generated from the VQ codebook, we proposed a parallel decoder consisting of a texture decoder and a main decoder. Those two decoders then interact with a texture warping module with deformable convolution. Equipped with the VQ codebook as a facial detail dictionary and the parallel decoder design, the proposed VQFR can largely enhance the restored quality of facial details while keeping the fidelity to previous methods.
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):
get_harvested_code_for_paper(arxiv_id="2205.06803")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2205.06803", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2205.06803")
Code
Syntology 15 code samples harvested from 1 repository linked to this paper: 9 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: official repository: 15 samples from 1 repository, 9 ran (8 with no instrument failure; 1 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.
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: 9 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. “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.
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 tencentarc/vqfr. “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 3 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.
b39cff2183f6ab2c · report
fixture: returned DCNv2Pack · level recorded 2026-09-22 7b32beb0e745f885 · report
fixture: returned InpFeatConv · level recorded 2026-09-22 a9032a215717b327 · report
fixture: returned ModulatedDeformConvFunction · level recorded 2026-09-22 78978c97f6293a19 · report
fixture: returned ModulatedDeformConvPack · level recorded 2026-09-22 c7e6e97e1951732e · report
fixture: returned ResnetBlock · level recorded 2026-09-22 0eb17d164a6a2ae8 · report
fixture: returned UpDownSample · level recorded 2026-09-22 1c7b1a47e3f2e5da · report
fixture: returned VQGANDecoder · level recorded 2026-09-22 dbdd8d8a22505791 · report
fixture: returned VQGANEncoder · level recorded 2026-09-22 56fbc8f16d71801d · report
fixture: signature logger_name:str/0/str, log_level:int/0/int, log_file:str/0/str · returned Logger · level recorded 2026-09-22 954bcb0ab2aff115 · report
7d041853e05afba5 · report
9ad02ae1b92be076 · report
34f1e2720da9e432 · report
a13b8d4c1525ed99 · report
c48bd8317e02c6f5 · 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 VQFR (graph method: VQFR). 17 bricks; individually on a fixture: 11 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.
- VQFRv1 entry · level 0 · unverified ·
a13b8d4c1525ed99 - GeneralizedQuantizer helper · level 0 · unverified ·
954bcb0ab2aff115 - InpFeatConv helper · level 1 · ran ·
7b32beb0e745f885 - MainDecoder model · level 0 · unverified ·
7d041853e05afba5 - VQGANDecoder helper · level 1 · ran ·
1c7b1a47e3f2e5da - VQGANEncoder helper · level 1 · ran ·
dbdd8d8a22505791 - build_quantizer helper · level 0 · unverified ·
c48bd8317e02c6f5 - ResnetBlock helper · level 1 · ran ·
c7e6e97e1951732e - TextureWarpingModule helper · level 0 · unverified ·
34f1e2720da9e432 - UpDownSample helper · level 1 · ran ·
0eb17d164a6a2ae8 - get_root_logger helper · level 1 · ran · our draft was wrong ·
56fbc8f16d71801d - DCNv2Pack helper · level 1 · ran ·
b39cff2183f6ab2c - get_dist_info helper · level 1 · ran ·
34c62f60981f053e - ModulatedDeformConvPack helper · level 1 · ran ·
78978c97f6293a19 - ModulatedDeformConv helper · level 0 · unverified ·
9ad02ae1b92be076 - ModulatedDeformConvFunction helper · level 1 · ran ·
a9032a215717b327 - Registry helper · level 1 · ran ·
2cd4dd2a6360b684
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="2205.06803") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
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