# A Camera-Native Talking-Head Video Dataset for Various Computer Vision Tasks

arXiv: https://arxiv.org/abs/2603.26763 · HTML: https://mlsanity.com/paper/2603.26763/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 42 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 16 of 16)

- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment](https://mlsanity.com/paper/2104.13371/) (2021)
- [BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond](https://mlsanity.com/paper/2012.02181/) (2020)
- [CelebV-HQ: A Large-Scale Video Facial Attributes Dataset](https://mlsanity.com/paper/2207.12393/) (2022)
- [VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution](https://mlsanity.com/paper/2205.03409/) (2022)
- [Investigating Tradeoffs in Real-World Video Super-Resolution](https://mlsanity.com/paper/2111.12704/) (2021)
- [A Technical Overview of AV1](https://mlsanity.com/paper/2008.06091/) (2020)
- [Generative Face Video Coding Techniques and Standardization Efforts: A Review](https://mlsanity.com/paper/2311.02649/) (2023)
- [DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation](https://mlsanity.com/paper/2410.07151/) (2024)
- [A crowdsourcing approach to video quality assessment](https://mlsanity.com/paper/2204.06784/) (2022)
- [Gemino: Practical and Robust Neural Compression for Video Conferencing](https://mlsanity.com/paper/2209.10507/) (2022)
- [VCD: A Video Conferencing Dataset for Video Compression](https://mlsanity.com/paper/2309.07376/) (2023)

## Abstract (arXiv)

Talking-head videos constitute a predominant content type in real-time communication, yet publicly available datasets for video processing research in this domain remain scarce and limited in signal fidelity. In this paper, we open-source a camera-native dataset of 838 talking-head recordings (approximately 210 minutes), each 15s in duration, captured from 799 participants across 443 camera-code categories in their natural environments. All recordings are stored using the FFV1 lossless codec, preserving the camera-native signal---uncompressed (24.7%) or MJPEG-encoded (75.3%)---without additional lossy processing. Each recording is annotated with a Mean Opinion Score (MOS) and ten perceptual quality tokens that jointly explain 64.4% of the MOS variance. From this corpus, we curate a stratified benchmarking subset of 120 clips in three content conditions: original, background blur, and background replacement. Codec efficiency evaluation across four datasets and four codecs, namely H.264, H.265, H.266, and AV1, yields VMAF BD-rate savings up to -71.3% (H.266) relative to H.264, with significant encoder×dataset (ηp2 = .112) and encoder×content condition (ηp2 = .149) interactions, demonstrating that both content type and background processing affect compression efficiency. A preliminary super-resolution evaluation with four SR models confirms that the dataset significantly affects absolute performance while preserving model rankings, demonstrating applicability beyond codec benchmarking. The dataset offers 5× the scale of the largest prior talking-head webcam dataset (838 vs. 160 clips) and preserves the camera-native signal without additional lossy compression, establishing a resource for benchmarking video compression, super-resolution, quality assessment, and enhancement models in real-time communication.