The paper introduces DirectSwap, a mask‑free video head‑swapping method that leverages a newly created cross‑identity paired dataset, HeadSwapBench. By synthesizing expression‑synchronized video pairs from real footage, the authors provide frame‑aligned ground truth for full‑reference evaluation of identity, expression, pose, reconstruction fidelity, and temporal stability. DirectSwap outperforms traditional same‑identity masked reconstruction, especially when head silhouettes change, and can restore non‑head content without external segmentation.
By Yanan Wang, Shengcai Liao, Panwen Hu, Xin Li, Fan Yang, Guangxi Liu, Xiaodan Liang
arXiv:2601.01352v2 Announce Type: replace
Abstract: Human identity-preserving text-to-video generation remains challenging under large changes in viewpoint, facial expression, illumination, and motio...
By Yixuan Lai, He Wang, Kun Zhou, Tianjia Shao
arXiv:2607. 22830v2 Announce Type: replace Abstract: In visual storytelling, human performances are central to creative intent and narrative meaning.
By Yuancheng Xu, Mingming He, Pablo Salamanca, Li Ma, Yash Kant, Emmett Steven, Paul Debevec, Ning Yu
Current identity customized video generation methodologies are predominantly limited to single-identity scenarios, as the lack of explicit identity separation mechanisms often leads to identity confusion in multi-identity settings. Existing multi-identity approaches, which directly extend single-identity frameworks by concatenating face images as input conditions, frequently result in unnatural facial expressions and motions, manifesting as the "copy-paste" phenomenon.
The paper introduces a zero‑shot subject‑driven video generation framework that eliminates the need for per‑subject tuning and large subject‑video datasets. It achieves this by separating identity injection—learned from subject‑image pairs—and motion‑awareness preservation—maintained with a small set of arbitrary videos, and optimizes both with stochastic switching and dropout techniques. Using CogVideoX‑5B, the method adapts a single model with only 200K subject‑image pairs and 4,000 arbitrary videos in 288 A100 GPU hours, representing roughly 1% of the compute required by previous zero‑shot baselines while preserving subject fidelity and motion quality.
By Daneul Kim, Jingxu Zhang, Wonjoon Jin, Sunghyun Cho, Qi Dai, Jaesik Park, Chong Luo
Face Video Restoration (FVR) aims to recover high-fidelity facial videos from degraded input while preserving identity and semantic consistency across frames. Existing methods often struggle to simultaneously address three key challenges: identity shift, viewpoint-entangled guidance, and perceptual realism.
arXiv:2607. 21434v1 Announce Type: cross Abstract: Video face swapping has no natural paired supervision: no real footage exists of one person's face performing another person's video.
By Logan Robbins
WildHSR introduces a lightweight adaptation of 3D foundation models to jointly recover metric cameras, scene geometry, and persistent person identities from monocular video. By generating pseudo‑scale labels from curated web footage and fine‑tuning a Scale Readout, the method predicts metric scale directly from foundation‑model tokens. It also exploits intermediate query‑key features to associate per‑frame bodies, enabling feed‑forward reconstruction that outperforms state‑of‑the‑art optimization‑based methods on several benchmarks while running at 10.1 fps.
By Jerrin Bright, John Zelek
arXiv:2609.13264v1 Announce Type: cross
Abstract: Generating human-centric videos that preserve both visual identity and person-specific expressive behavior remains a fundamental challenge. In additi...
By Pokrzywa Baptiste, Nabyl Quignon, Yara Bahram, Muhammad Osama Zeeshan, Antitza Dantcheva, Eric Granger
arXiv:2608. 20336v1 Announce Type: new Abstract: Identity-preserving image generation becomes increasingly unreliable when a scene must contain many specified people.
By Hengyuan Xu, Qixun Wang, Yiji Cheng, Miles Yang, Zhao Zhong, Wei Cheng, Xingjun Ma, Yu-gang Jiang
CogCanvas is a new benchmark for multi-subject reference-based image generation, featuring 1,952 curated reference images of 100 celebrities, 115 objects/fashion items, and 29 real-world backgrounds. It generates 1,361 compositional prompts with 2–5 people, using a pipeline that includes DINOv2 deduplication, aesthetic filtering, and automated graph derivation for interaction and positioning. The benchmark evaluates three tasks—reference-based multi-human-object generation, text-to-image compositional generation, and reference retrieval—under a six-axis protocol, and introduces BG‑Sim and Attr‑VQA metrics to assess background fidelity and attribute binding.
By Long-Bao Nguyen, Quang-Khai Le, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le
Identity-preserving image generation becomes increasingly unreliable when a scene must contain many specified people. Beyond retaining each identity, the model must bind every reference to a distinct person and location, while training-time identity losses must establish correspondence among several noisy predicted faces.