research
∙
05/22/2023
ControlVideo: Training-free Controllable Text-to-Video Generation
Text-driven diffusion models have unlocked unprecedented abilities in im...
share
research
∙
04/24/2023
Segment Anything in 3D with NeRFs
The Segment Anything Model (SAM) has demonstrated its effectiveness in s...
research
∙
03/14/2023
USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation
Seed area generation is usually the starting point of weakly supervised ...
research
∙
07/31/2022
SdAE: Self-distillated Masked Autoencoder
With the development of generative-based self-supervised learning (SSL) ...
research
∙
07/04/2022
A Survey on Label-efficient Deep Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction
The rapid development of deep learning has made a great progress in segm...
research
∙
12/23/2017