Dark Matters: VAE-Aware HDR Encoding for SDR-to-HDR Video Reconstruction
cs.CV, cs.AI
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- Towards Efficient SDRTV-to-HDRTV by Learning from Image Formation
- Semantic Aware Diffusion Inverse Tone Mapping
- LTX-Video: Realtime Video Latent Diffusion
- In-Context LoRA for Diffusion Transformers
- HDR Video Generation via Latent Alignment with Logarithmic Encoding
- Wan: Open and Advanced Large-Scale Video Generative Models
- LEDiff: Latent Exposure Diffusion for HDR Generation
- DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models
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