FreeDeshadow: Shadow Removal for User-Specified Objects With Multimodal Prompts
cs.CV
Submitted: 2026-11-10
Updated: 2026-11-10
Project page: https://freedeshadow.github.io
Terminology
Sources
- Step1X-Edit: A Practical Framework for General Image Editing
- Qwen-Image Technical Report
- ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling
- UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
- RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details
- Qwen2.5-VL Technical Report
- Shadow Generation for Composite Image in Real-world Scenes
- VisualPRM: An Effective Process Reward Model for Multimodal Reasoning
- MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- OmniGen: Unified Image Generation
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