Optical Flow
- SPyNet: Spatial Pyramid Network for Optical Flow
- PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
- SKFlow: Learning Optical Flow with Super Kernels
Video frame interpolation
- BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation
- Asymmetric Bilateral Motion Estimation for Video Frame Interpolation (ABME)
- BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation
- Quadratic Video Interpolation
- Video Frame Interpolation with Transformer
- AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation
- A Unified Pyramid Recurrent Network for Video Frame Interpolation
Image compression
- VARIATIONAL IMAGE COMPRESSION WITH A SCALE HYPERPRIOR
- Joint Autoregressive and Hierarchical Priors for Learned Image Compression
- Content-aware Masked Image Modeling Transformer for Stereo Image Compression
- Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules
- DPICT: Deep Progressive Image Compression Using Trit-Planes
- Context-Based Trit-Plane Coding for Progressive Image Compression
- ANFIC: Image Compression Using Augmented Normalizing Flows
Video compression
P-frame codec
- DVC: AnEnd-to-end Deep Video Compression Framework
- VCT: AVideo Compression Transformer
- Deep Contextual Video Compression (DCVC)
- Neural Video Compression with Diverse Contexts (DCVC-DC)
B-frame codec
- B-CANF: Adaptive B-Frame Coding With Conditional Augmented Normalizing Flows
- Conditional Variational Autoencoders for Hierarchical B-frame Coding
- MaskCRT: Masked Conditional Residual Transformer for Learned Video Compression
- OMRA: ONLINE MOTION RESOLUTION ADAPTATION TO REMEDY DOMAIN SHIFT IN LEARNED HIERARCHICAL B-FRAME CODING
- Hierarchical B-frame Video Coding Using Two-Layer CANF without Motion Coding
기타 알아야 할것
- Correlation (cost) volume
- Forward warping / Backward warping
- Entropy (coding)
- I, B, P frame
