Papers › Improving the Efficiency and Robustness of Deepfakes Detection through Precise...

Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features

9 Apr 2021CVPR 2021 1arXiv:2104.04480archive 2025-07-28

Zekun Sun, Yujie Han, Zeyu Hua, Na Ruan, Weijia Jia

Deepfakes is a branch of malicious techniques that transplant a target face to the original one in videos, resulting in serious problems such as infringement of copyright, confusion of information, or even public panic. Previous efforts for Deepfakes videos detection mainly focused on appearance features, which have a risk of being bypassed by sophisticated manipulation, also resulting in high model complexity and sensitiveness to noise. Besides, how to mine the temporal features of manipulated videos and exploit them is still an open question. We propose an efficient and robust framework named LRNet for detecting Deepfakes videos through temporal modeling on precise geometric features. A novel calibration module is devised to enhance the precision of geometric features, making it more discriminative, and a two-stream Recurrent Neural Network (RNN) is constructed for sufficient exploitation of temporal features. Compared to previous methods, our proposed method is lighter-weighted and easier to train. Moreover, our method has shown robustness in detecting highly compressed or noise corrupted videos. Our model achieved 0.999 AUC on FaceForensics++ dataset. Meanwhile, it has a graceful decline in performance (-0.042 AUC) when faced with highly compressed videos.

PaperPDFConference PDFCodeCode Syntology ran

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 16 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 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) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 16 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

frederickszk/LRNet officialmentioned in papermentioned on GitHubtfMITSyntology: 16 samples, 11 ran (0 instrument-failed) · 5 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

16 samples harvested: 11 ran (of which 0 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) · 5 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.

11ran
5unverified

Licence: 0 of the 16 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 frederickszk/LRNet. “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”. “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.

frederickszk/LRNet official repository 16 samples, 11 ran (0 instrument-failed) · 5 unverified
calculate_face_distance demo/utils/landmark_utils.py ran fingerprinted MIT (permissive) · 2051a96bbb72d3d5 · report fixture: signature shape_prev:ndarray/2/float, shape_curr:ndarray/2/float · returned float64 · level recorded 2026-09-25
calculate_face_size calibrator/LC.py ran MIT (permissive) · afe7866194ad8ad3 · report fixture: signature shape:ndarray/2/float · returned float64 · level recorded 2026-09-25
check_and_merge calibrator/LC.py ran MIT (permissive) · fe7e329296d721d1 · report fixture: signature location:list/1/ndarray, forward:list/1/ndarray, feedback:list/1/ndarray, P_predict:ndarray/1/float, status_fw:ndarray/2/int, status_fb:ndarray/2/int · returned tuple · level recorded 2026-09-25
generate_weight demo/utils/deprecated.py ran MIT (permissive) · 57bd091b62ceeb21 · report fixture: signature patch_size:int/0/int · returned ndarray · level recorded 2026-09-25
get_data in 223 papers training/data_utils.py ran MIT (permissive) · 3d6516d06197ac78 · report fixture: signature path:str/0/str, fake:int/0/int, block:int/0/int · returned tuple · level recorded 2026-09-25
get_data_for_test demo/classify.py ran MIT (permissive) · f967450a45f894d6 · report fixture: signature path:str/0/str, fake:int/0/int, block:int/0/int · returned tuple · level recorded 2026-09-25
get_data_for_test training/data_utils.py ran MIT (permissive) · ffa491400e748f12 · report fixture: signature path:str/0/str, fake:int/0/int, block:int/0/int · returned tuple · level recorded 2026-09-25
load_yaml in 107 papers training/configs/loader.py ran MIT (permissive) · 3bffc6edf7b94a8f · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-25
merge_video_prediction demo/classify.py ran MIT (permissive) · 6f587a3468f0c200 · report fixture: signature mix_prediction:list/1/float, s2v:list/1/str, vc:dict/0/? · returned list · level recorded 2026-09-25
merge_video_prediction training/data_utils.py ran MIT (permissive) · 4ca0cdd26ad809f0 · report fixture: signature mix_prediction:list/1/float, s2v:list/1/int, vc:dict/0/? · returned list · level recorded 2026-09-25
shape_to_face calibrator/LC.py ran MIT (permissive) · f1e34b9b56f48a35 · report fixture: signature shape:ndarray/2/float, width:int/0/int, height:int/0/int, scale:float/0/float, assign_face_size:NoneType/0/?, shift_threshold:float/0/float, center_prev:NoneType/0/? · returned tuple · level recorded 2026-09-25
lk_track demo/utils/deprecated.py unverified MIT (permissive) · 2b5c147200484bac · report
load_data_test training/model_tf.py unverified MIT (permissive) · 2a53262ee3c69361 · report
load_data_train training/model_tf.py unverified MIT (permissive) · 4608835f4e2c1dc1 · report
predict in 126 papers demo/classify.py unverified MIT (permissive) · ac93c18af42c2c35 · report
track_bidirectional demo/utils/deprecated.py unverified MIT (permissive) · d0e3a6001a5c6f64 · report

Tasks

Open-Ended Question Answering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

LRNet

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