# ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning

arXiv: https://arxiv.org/abs/2607.01677 · HTML: https://mlsanity.com/paper/2607.01677/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 38 of its 42 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 38)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Virtual KITTI 2](https://mlsanity.com/paper/2001.10773/) (2020)
- [OminiControl: Minimal and Universal Control for Diffusion Transformer](https://mlsanity.com/paper/2411.15098/) (2024)
- [Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos](https://mlsanity.com/paper/2304.01186/) (2023)
- [Consistent Video Depth Estimation](https://mlsanity.com/paper/2004.15021/) (2020)
- [Video Depth Anything: Consistent Depth Estimation for Super-Long Videos](https://mlsanity.com/paper/2501.12375/) (2025)
- [DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos](https://mlsanity.com/paper/2409.02095/) (2024)
- [Robust Consistent Video Depth Estimation](https://mlsanity.com/paper/2012.05901/) (2020)
- [ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals](https://mlsanity.com/paper/1905.02082/) (2019)
- [In-Context LoRA for Diffusion Transformers](https://mlsanity.com/paper/2410.23775/) (2024)
- [Less-to-More Generalization: Unlocking More Controllability by In-Context Generation](https://mlsanity.com/paper/2504.02160/) (2025)
- [OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models](https://mlsanity.com/paper/2502.01061/) (2025)
- [Long Context Tuning for Video Generation](https://mlsanity.com/paper/2503.10589/) (2025)
- [Learning Temporally Consistent Video Depth from Video Diffusion Priors](https://mlsanity.com/paper/2406.01493/) (2024)
- [Controllable Video Generation: A Survey](https://mlsanity.com/paper/2507.16869/) (2025)
- [DreamO: A Unified Framework for Image Customization](https://mlsanity.com/paper/2504.16915/) (2025)
- [Follow-Your-Creation: Empowering 4D Creation through Video Inpainting](https://mlsanity.com/paper/2506.04590/) (2025)
- [OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling](https://mlsanity.com/paper/2509.12201/) (2025)
- [Exploiting temporal consistency for real-time video depth estimation](https://mlsanity.com/paper/1908.03706/) (2019)
- [Insert Anything: Image Insertion via In-Context Editing in DiT](https://mlsanity.com/paper/2504.15009/) (2025)
- [Depth Any Video with Scalable Synthetic Data](https://mlsanity.com/paper/2410.10815/) (2024)

## Abstract (arXiv)

Monocular video depth estimation requires temporal consistency, geometric accuracy, and generalization across diverse scenarios, yet existing methods struggle to achieve all three simultaneously. Discriminative models excel at per-frame accuracy but suffer from temporal drift due to limited context windows, while generative methods improve consistency and generalization at the cost of extensive training data (10M+ samples) and lack of geometric precision. In response to these issues, we introduce ICDepth, a framework that adapts pre-trained text-to-video diffusion transformers for video depth estimation via In-Context Conditioning (ICC), leveraging their rich spatial-temporal priors. To address key challenges in transferring ICC from generation to dense prediction, we propose: (1)~SAND-Attention, which ensures precise spatial-temporal alignment via shared RoPE and enforces unidirectional attention to prevent noise contamination; (2)~SRFM, which injects DINOv2 semantic and resolution priors to enhance geometric precision. ICDepth achieves state-of-the-art results on multiple benchmarks with remarkable data efficiency, trained on only 0.8M frames (6--13× less than competing generative methods), while demonstrating strong zero-shot generalization to diverse domains.