arXiv Computer Vision October 9, 2026 By Saransh Suri, Shivang Agarwal, Mayank Vatsa, Richa Singh

Adaptive Adversarial Augmentation for Controllable Face Synthesis

Read the original on arXiv Computer Vision →

The paper introduces Ensemble Feedback Controllable Synthesis (EFCS), a framework that generates diverse, challenging synthetic face images while preserving visual realism. EFCS improves distributional variability, achieving higher FID and KID scores than single‑feedback or random synthesis, yet maintains high precision. Models trained on EFCS data outperform baselines on multiple benchmarks, and the authors provide an analytical formulation linking perturbation difficulty, sample utility, and performance degradation to guide synthetic data complexity.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Machine Learning

Sep 4

A Real-Calibrated Synthetic-First Data Engine

The paper introduces the Real‑Calibrated Synthetic‑First Data Engine, a modular pipeline that integrates controllable diffusion‑based synthetic image generation with multi‑stage curation, filtering, and optional uncertainty‑driven selection and human verification. Designed as a CLI‑based framework, it allows independent configuration of generation, filtering, selection, and validation modules to enhance reproducibility and flexibility in real‑world data workflows. Empirical tests on human pose estimation demonstrate that synthetic data can boost a real‑data baseline when used as low‑cost augmentation, though synthetic‑only training still lags behind real‑only performance, underscoring the importance of data‑centric orchestration in low‑data regimes.

By Yukang Shen, Zhiguo Liu, Yingshu Li, Yan Huang

agents diffusion computer-vision data-engineering

arXiv Computer Vision

Aug 25

Photorealistic Novel View Synthesis of Human Faces using Next-Scale Transformers

arXiv:2608.23410v1 Announce Type: new Abstract: Photorealistic novel view synthesis of people remains challenging at high spatial resolutions and across multiple target cameras, where preserving iden...

By Federico Stella, Fei Jiang, Zhongshi Jiang, Zohar Barzelay, Emanuel Garbin, Amin Jourabloo, Liuhao Ge

llms diffusion

arXiv AI

Jul 17

Benchmarking Face Recognition without Real Faces

arXiv:2607. 14932v1 Announce Type: cross Abstract: Synthetic face datasets have become effective enough to train face recognition models with accuracy rivaling that of models trained on real photographs.

By Pawe{\l} Borsukiewicz, Daniele Lunghi, Wendk\^uuni C. Ou\'edraogo, Jacques Klein, Tegawend\'e F. Bissyand\'e

llms benchmarks safety

arXiv Machine Learning

Aug 11

Compatibility of Face Embeddings Across Deep Neural Networks

arXiv:2604. 07282v2 Announce Type: replace-cross Abstract: Automated face recognition has made rapid strides over the past decade due to the unprecedented rise of deep neural network (DNN) models that can be trained for domain-specific tasks.

By Fizza Rubab, Yiying Tong, Arun Ross

rag multimodal safety

arXiv AI

Jul 21

Identity-Consistent Expression Fields: A Disentangled Neural Radiance Field Framework for Few-Shot Facial Expression Synthesis

arXiv:2607. 16287v1 Announce Type: cross Abstract: Neural Radiance Fields (NeRF) have enabled photorealistic novel-view synthesis of 3D scenes and, in the facial domain, have been extended to reconstruct and animate 3D face models from a small number of images.

By Minh Tran

arXiv Computer Vision

Sep 1

Identity-Conditioned Latent Consistency Distillation for Face Synthesis

arXiv:2608.31053v1 Announce Type: new Abstract: Diffusion models have achieved strong results in high-fidelity image synthesis, but their iterative sampling process makes large-scale generation compu...

By Tiago Kienen Chaves, Bernardo Biesseck, David Menotti

rag diffusion efficiency