@ModelScope2022: Marigold V2 turns an image-editing DiT into a single-step model for sharp, detailed dense prediction. Apache 2.0. https…
Summary
Marigold V2 transforms an image-editing Diffusion Transformer into a single-step model for sharp dense prediction, achieving best zero-shot results in depth estimation and related tasks with Apache 2.0 license.
View Cached Full Text
Cached at: 09/14/26, 11:26 AM
Marigold V2 turns an image-editing DiT into a single-step model for sharp, detailed dense prediction.📜 Apache 2.0. 🤖 https://modelscope.ai/models/huawei-bayerlab/marigold-v2-0… 📄 https://modelscope.ai/papers/2609.08084…
🏆 Best zero-shot results across all evaluated depth datasets among models trained on comparable data. AbsRel improves by 16%–26% over the previous best on KITTI and ETH3D. 🔍 Fur, foliage, fine wires, and object boundaries stay crisp. The two-stage iREPA and SinkLoss recipe tackles the smoothing and flying-pixel artifacts common in diffusion-based depth models. 🧩 The same framework reaches SOTA results in depth completion, see-through depth, surface normals, and intrinsic image decomposition. Depth completion records the lowest RMSE across all four reported benchmarks. ⚡ A pretrained Qwen-Image-Edit DiT becomes a single-step dense predictor through lightweight adaptation. Training takes less than a week on one 32 GB GPU.
Similar Articles
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
Marigold V2 repurposes diffusion transformers for monocular depth estimation via single-step inference and a novel fine-tuning protocol, achieving sharper depth maps and significant improvements on benchmarks like KITTI and ETH3D.
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
LLaDA-Image presents a unified framework that combines a 6B diffusion transformer with a frozen vision-language module for generating photorealistic images with precise editing, achieving state-of-the-art results among open-source models through efficient training and fast inference.
MMDiff: Extending Diffusion Transformers for Multi-Modal Generation
MMDiff extends frozen diffusion transformers into multi-modal generative systems using lightweight decoders, achieving significant improvements in semantic segmentation and other perceptual tasks through multi-timestep feature fusion.
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
ReChannel adapts pretrained diffusion transformers (e.g., FLUX-Klein) for dense prediction tasks by mapping tokens directly to pixel-space patches, achieving state-of-the-art results on trimap-free matting, KITTI depth, and referring segmentation with minimal additional parameters.
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
PointDiT presents a minimalist pixel-space diffusion transformer using a plain ViT architecture for monocular geometry estimation, outperforming complex latent-based models while maintaining simplicity and robustness in ambiguous regions.