Source-Face Authenticity Detection for 3D Gaussian Heads Reconstructed from a Single Portrait: A Benchmark and Dedicated Detector

• URL: http://arxiv.org/abs/2608.23984v1
• Date: Tue, 25 Aug 2026 02:24:16 GMT
• Title: Source-Face Authenticity Detection for 3D Gaussian Heads Reconstructed from a Single Portrait: A Benchmark and Dedicated Detector
• Abstract summary: Single-image 3D Gaussian head reconstruction has enabled highly realistic and freely renderable digital heads from a single portrait.<n>However, reconstruction and rendering can weaken the traces forgery in the source portrait, making the resulting 3D face difficult to classify whether its underlying face is real or fake.<n>We propose a detector trained with a two-stage strategy. In Stage I, masked autoencoding encourages the visual backbone to retain the fine-grained appearance information required for local reconstruction, while multi-view contrastive learning enforces feature consistency across rendered views of the same head.<n>Experiments show that our method achieves the highest accuracy and
• Score: 15.120546308798957
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in single-image 3D Gaussian head reconstruction have enabled highly realistic and freely renderable digital heads from a single portrait. However, reconstruction and rendering can weaken the forgery traces in the source portrait, making the resulting 3D face difficult to classify whether its underlying face is real or fake, and thereby posing risks to identity authentication and face privacy. To study this problem, we introduce the first large-scale benchmark for this task by collecting real portraits and fake portraits from multiple sources and evaluate representative existing detectors on this benchmark, revealing their lack of explicit mechanisms for retaining fine-grained information and maintaining feature consistency across rendered views. To directly address these two limitations, we propose a detector trained with a two-stage strategy. In Stage I, masked autoencoding encourages the visual backbone to retain the fine-grained appearance information required for local reconstruction, while multi-view contrastive learning enforces feature consistency across rendered views of the same head. Since CLS tokens at different depths exhibit complementary spatial attention patterns, Stage II freezes the adapted backbone and concatenates low-, middle-, and high-level CLS tokens for classification. Experiments show that our method achieves the highest accuracy and ranks first across all reported metrics among the evaluated detectors.

Related papers

• Visual Prompting Meets Feature Reconstruction-Based Anomaly Detection with Dual-Teacher Supervision [7.548589503544904]
  We introduce a visual prompting pipeline that isolates objects using foreground-background masking.<n>We also introduce a mechanism for unfreezing the teacher in student-teacher models to improve domain adaptability.<n>We achieve a 3.5 percentage point improvement over the previous state-of-the-art on the challenging AeBAD dataset.
  arXiv  Detail & Related papers  (2026-06-08T15:52:05Z)
• 3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification [1.621606615628714]
  Aerial-Ground Re-Identification (AG-ReID) is constrained by the viewpoint-domain gap.<n>We are first to address this challenge by formalizing the Single-View AG-ReID setting.<n>We propose 3D Lifting-based Elevated Novel-view Synthesis (3D-LENS)
  arXiv  Detail & Related papers  (2026-04-29T10:38:48Z)
• GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learning [11.364765496753074]
  3D Anomaly Detection is an emerging task that aims to detect anomalies in a target dataset without any target training data.<n>Current methods adapt CLIP by projecting 3D point clouds into 2D representations, but they face challenges.<n>We propose the Geometry-Aware Prompt and Synergistic View Representation Learning framework, which enables the model to identify geometric anomalies through a two-stage learning process.
  arXiv  Detail & Related papers  (2026-02-22T14:30:41Z)
• ExposeAnyone: Personalized Audio-to-Expression Diffusion Models Are Robust Zero-Shot Face Forgery Detectors [58.45131932883374]
  We propose a fully self-supervised approach to detect deepfakes in videos.<n>Our model computes the identity distances between suspected videos and personalized subjects via diffusion reconstruction errors.<n>Our method is highly robust to corruptions such as blur and compression, highlighting the applicability in real-world face forgery detection.
  arXiv  Detail & Related papers  (2026-01-05T18:59:54Z)
• Robust Deepfake Detection for Electronic Know Your Customer Systems Using Registered Images [29.349824933680956]
  We present a deepfake detection algorithm specifically designed for electronic Know Your Customer (eKYC) systems.<n>Our approach evaluates the video's authenticity by detecting temporal inconsistencies in identity vectors extracted by face recognition models.<n>In addition to processing video input, the algorithm utilizes a registered image (assumed to be genuine) to calculate identity discrepancies.
  arXiv  Detail & Related papers  (2025-07-30T12:16:27Z)
• UniForensics: Face Forgery Detection via General Facial Representation [60.5421627990707]
  High-level semantic features are less susceptible to perturbations and not limited to forgery-specific artifacts, thus having stronger generalization. We introduce UniForensics, a novel deepfake detection framework that leverages a transformer-based video network, with a meta-functional face classification for enriched facial representation.
  arXiv  Detail & Related papers  (2024-07-26T20:51:54Z)
• Effective Adapter for Face Recognition in the Wild [72.75516495170199]
  We tackle the challenge of face recognition in the wild, where images often suffer from low quality and real-world distortions. Traditional approaches-either training models directly on degraded images or their enhanced counterparts using face restoration techniques-have proven ineffective. We propose an effective adapter for augmenting existing face recognition models trained on high-quality facial datasets.
  arXiv  Detail & Related papers  (2023-12-04T08:55:46Z)
• Instant Multi-View Head Capture through Learnable Registration [62.70443641907766]
  Existing methods for capturing datasets of 3D heads in dense semantic correspondence are slow. We introduce TEMPEH to directly infer 3D heads in dense correspondence from calibrated multi-view images. Predicting one head takes about 0.3 seconds with a median reconstruction error of 0.26 mm, 64% lower than the current state-of-the-art.
  arXiv  Detail & Related papers  (2023-06-12T21:45:18Z)
• Semantic-aware One-shot Face Re-enactment with Dense Correspondence Estimation [100.60938767993088]
  One-shot face re-enactment is a challenging task due to the identity mismatch between source and driving faces. This paper proposes to use 3D Morphable Model (3DMM) for explicit facial semantic decomposition and identity disentanglement.
  arXiv  Detail & Related papers  (2022-11-23T03:02:34Z)
• Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis [69.09526348527203]
  Deep generative models have led to highly realistic media, known as deepfakes, that are commonly indistinguishable from real to human eyes. We propose a novel fake detection that is designed to re-synthesize testing images and extract visual cues for detection. We demonstrate the improved effectiveness, cross-GAN generalization, and robustness against perturbations of our approach in a variety of detection scenarios.
  arXiv  Detail & Related papers  (2021-05-29T21:22:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.