Controllable Style Transfer via Test-time Training of Implicit Neural Representation A controllable style transfer framework based on Implicit Neural Representation that pixel-wisely controls the stylized output via test-time training. November 28, 2022 · 1 min read
ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization A semi-supervised learning framework that leverages the consistency regularization between the model’s predictions from two strongly-augmented views of an image, weighted by a confidence of pseudo-labels. November 27, 2022 · 1 min read
Meta-Learned Initialization For 3D Human Recovery A framework for 3D human recovery from a single image that integrates meta-learning with test-time optimization. November 26, 2022 · 1 min read
Joint Learning of Feature Extraction and Cost Aggregation for Semantic Correspondence A semantic matching framework that jointly learns both feature extraction and cost aggregation modules by employing a confidence-aware contrastive loss. November 23, 2022 · 1 min read