DynOLAT: OLAT Video Prediction for Controllable Dynamic Full-Body Relighting
cs.CV
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- RelightMaster: Precise Video Relighting with Multi-plane Light Images
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- LBM: Latent Bridge Matching for Fast Image-to-Image Translation
- Extending Context Window of Large Language Models via Positional Interpolation
- MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos
- Relighting4D: Neural Relightable Human from Videos
- ScribbleLight: Single Image Indoor Relighting with Scribbles
- RelightVid: Temporal-Consistent Diffusion Model for Video Relighting
- UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting
- Auto-Encoding Variational Bayes
- IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation
- UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback
- DreamLight: Towards Harmonious and Consistent Image Relighting
- Learning Physics-guided Face Relighting under Directional Light
- High-Resolution Image Synthesis with Latent Diffusion Models
- Relightable Holoported Characters: Capturing and Relighting Dynamic Human Performance from Sparse Views
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
- D-Rex : Diffusion Rendering for Relightable Expressive Avatars
- Wan: Open and Advanced Large-Scale Video Generative 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