Iris-Z: Scaling One Generative Model Past Specialist Geometry Models
cs.CV, cs.AI
Submitted: 2026-11-11
Updated: 2026-11-11
Code: https://github.com/speridlabs/iris-z-sdk
Terminology
Sources
- Scaling Laws for Neural Language Models
- Training Compute-Optimal Large Language Models
- Video models are zero-shot learners and reasoners
- Image Generators are Generalist Vision Learners
- Emerging Properties in Unified Multimodal Pretraining
- PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation
- MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
- MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
- Depth Anything 3: Recovering the Visual Space from Any Views
- Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
- Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
- Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer
- ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth
- DepthFM: Fast Monocular Depth Estimation with Flow Matching
- Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
- DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
- LDM3D: Latent Diffusion Model for 3D
- Aether: Geometric-Aware Unified World Modeling
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