Similar Items: Rebalancing gradient to improve self-supervised co-training of depth, odometry and optical flow predictions
- Foundation AI Models for Aerosol Optical Depth Estimation from PACE Satellite Data
- Rethinking Dense Optical Flow without Test-Time Scaling
- Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements
- RD-ViT: Recurrent-Depth Vision Transformer for Semantic Segmentation with Reduced Data Dependence Extending the Recurrent-Depth Transformer Architecture to Dense Prediction
- Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision
- AnchorD: Metric Grounding of Monocular Depth Using Factor Graphs