Python Trending (@pythontrending)
CVPR 2026에서 발표된 'PersonaLive'는 실시간 스트리밍을 위한 표현력 있는 초상 이미지 애니메이션 기술이다. 이 연구는 AI 기반 얼굴 애니메이션의 사실감과 인터랙티브성을 크게 향상시켜, 가상 캐릭터나 아바타 방송 등 다양한 미디어 응용 가능성을 보여준다.
Satellite Earth-observation (EO) time series in the optical and microwave ranges of the electromagnetic spectrum are often irregular due to orbital patterns and cloud obstruction. Compositing addresses these issues but loses information with respect to vegetation phenology, which is critical for many downstream tasks. Instead, we present TESSERA, a pixel-wise foundation model for multi-modal (Sentinel-1/2) EO time series that learns robust, label-efficient embeddings. During model training, TESSERA uses Barlow Twins and sparse random temporal sampling to enforce invariance to the selection of valid observations. We employ two key regularizers: global shuffling to decorrelate spatial neighborhoods and mix-based regulation to improve invariance under extreme sparsity. We find that for diverse classification, segmentation, and regression tasks, TESSERA embeddings deliver state-of-the-art accuracy with high label efficiency, often requiring only a small task head and minimal computation. To democratize access, adhere to FAIR principles, and simplify use, we release global, annual, 10m, pixel-wise int8 embeddings together with open weights/code and lightweight adaptation heads, thus providing practical tooling for large-scale retrieval and inference at planetary scale. The model training/inference code, downstream task code, and pre-generated embeddings can be accessed at https://github.com/ucam-eo
lalmei
sayzard
Anil Madhavapeddy