Perceptual Distortion for Overfitted Video Coding: Sliced Matching in Space, Error Alignment in Time
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/Orange-OpenSource/Cool-Chic
Terminology
Sources
- COIN: COmpression with Implicit Neural representations
- Generative Neural Video Compression via Video Diffusion Prior
- Wasserstein Distortion: Unifying Fidelity and Realism
- Cool-chic 5.0: Faster Encoding and Inter-Feature Entropy Modeling for Overfitted Image Compression
- Cool-chic video: Learned video coding with 800 parameters
- Improved Encoding for Overfitted Video Codecs
- Efficient Sub-pixel Motion Compensation in Learned Video Codecs
- A Sliced Wasserstein Loss for Neural Texture Synthesis
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs