Pith. sign in

REVIEW 13 cited by

FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1912.13457 v3 pith:SMIZZSHN submitted 2019-12-31 cs.CV

Lingzhi Li , Jianmin Bao , Hao Yang , Dong Chen , Fang Wen This is my paper
classification cs.CV
keywords faceattributesswappingnoveltargetadaptivelyawarefaceshifter
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this work, we propose a novel two-stage framework, called FaceShifter, for high fidelity and occlusion aware face swapping. Unlike many existing face swapping works that leverage only limited information from the target image when synthesizing the swapped face, our framework, in its first stage, generates the swapped face in high-fidelity by exploiting and integrating the target attributes thoroughly and adaptively. We propose a novel attributes encoder for extracting multi-level target face attributes, and a new generator with carefully designed Adaptive Attentional Denormalization (AAD) layers to adaptively integrate the identity and the attributes for face synthesis. To address the challenging facial occlusions, we append a second stage consisting of a novel Heuristic Error Acknowledging Refinement Network (HEAR-Net). It is trained to recover anomaly regions in a self-supervised way without any manual annotations. Extensive experiments on wild faces demonstrate that our face swapping results are not only considerably more perceptually appealing, but also better identity preserving in comparison to other state-of-the-art methods.

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SRAP: SVD-Refined Adversarial Perturbations for Imperceptible Face-Swap Defense

    cs.CV 2026-08 conditional novelty 6.0 of 10

    SRAP combines per-channel truncated SVD and an identity-importance mask to make PGD perturbations for face-swap defense more imperceptible while retaining competitive identity disruption.

  2. Adversarial Deepfake Generation and an Investigation of Purification-Based Adversarial Detection

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Under median-3 purification, the raw logit shift of the EFFORT detector separates adversarial from clean images with AUROC 0.81–0.98 across four attack types, but only at JPEG quality >= 80.

  3. PhantomSeal: Proactive Deepfakes Defense with Identity/Context Protection and Forensic Tracing

    cs.CR 2026-07 conditional novelty 6.0 of 10

    A single perturbation can steer face-swap outputs toward a chosen 'cloak' identity, giving both identity/context protection and forensic tracing.

  4. Seeing Through Deepfakes: A Human-Inspired Framework for Multi-Face Detection

    cs.CV 2025-07 conditional novelty 6.0 of 10

    HICOM is a multi-face deepfake detection framework whose four modules are each inspired by cues that humans reportedly use to spot fake faces, achieving state-of-the-art frame-level complete detection on existing benchmarks.

  5. Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Pixel-wise temporal frequency features, computed by a 1D Fourier transform along the time axis after median filtering, improve cross-dataset and cross-synthesis deepfake video detection over stacked spatial-frequency ...

  6. InfoDense: Density-Aware Regional Decisive Replay for Memory-Efficient Incremental Face Forgery Detection

    cs.CV 2026-07 conditional novelty 5.0 of 10

    InfoDense replays only density-ranked, forgery-decisive face fragments rather than full images, cutting memory use and improving incremental deepfake detection.

  7. Evaluating Deepfake Detectors in the Wild

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Modern deepfake detectors, evaluated on a new 500,000 image in-the-wild style benchmark built with SimSwap and Inswapper, mostly fail to generalize and degrade under simple image manipulations.

  8. Scaling of strong-field spherical dynamos

    physics.geo-ph 2025-07 unverdicted novelty 5.0 of 10

    In spherical dynamo simulations, the strong-field branch persists toward Earth-like parameters, with a new force-balance diagnostic that flags it, and bounded scaling laws for its onset.

  9. Learning Counterfactually Decoupled Attention for Open-World Model Attribution

    cs.CV 2025-06 conditional novelty 5.0 of 10

    CDAL adds a counterfactual attention branch to open-world model attribution, improving novel-attack attribution by several points on OW-DFA and OSMA.

  10. Robust Deepfake Detection for Electronic Know Your Customer Systems Using Registered Images

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A video deepfake detector for eKYC that combines temporal identity-vector differences with differences against a registered photo, and shows robustness to image degradation.

  11. Visual Language Models as Zero-Shot Deepfake Detectors

    cs.CV 2025-07 conditional novelty 4.0 of 10

    Zero-shot VLMs scored by normalized yes/no token probabilities beat most trained deepfake detectors on a new SimSwap dataset, and a lightly fine-tuned InstructBLIP is near-perfect on DFDC-P.

  12. De-Fake: Style based Anomaly Deepfake Detection

    cs.CV 2025-07 reject novelty 3.0 of 10

    A style-feature face-swap detector that requires a reference photo, with flawed threshold arithmetic and invalid external tests.

  13. Controllable and Expressive One-Shot Video Head Swapping

    cs.CV 2025-06

Pith tools