Similar Items: Rethinking Dense Optical Flow without Test-Time Scaling
- Rebalancing gradient to improve self-supervised co-training of depth, odometry and optical flow predictions
- Linearizing Vision Transformer with Test-Time Training
- RD-ViT: Recurrent-Depth Vision Transformer for Semantic Segmentation with Reduced Data Dependence Extending the Recurrent-Depth Transformer Architecture to Dense Prediction
- Flow-OPD: On-Policy Distillation for Flow Matching Models
- Foundation AI Models for Aerosol Optical Depth Estimation from PACE Satellite Data
- Solving Minimal Problems Without Matrix Inversion Using FFT-Based Interpolation