Faces as light probes for relighting

A probabilistic approach to realistic face synthesis with a single uncalibrated image

Time-of-flight sensor and color camera calibration for multi-view acquisition

A subspace model-based approach to face relighting under unknown lighting and poses

Scribble-Guided Diffusion for Training-free Text-to-Image Generation

Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation

Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification

No Thing, Nothing: Highlighting Safety-Critical Classes for Robust LiDAR Semantic Segmentation in Adverse Weather

DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models

DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation