# Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation

arXiv: https://arxiv.org/abs/2512.23705 · HTML: https://mlsanity.com/paper/2512.23705/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 64 of its 80 references that are in the map.
- First posted on arXiv 29 Dec 2025.

## 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 64)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [Flow Matching Guide and Code](https://mlsanity.com/paper/2412.06264/) (2024)
- [MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision](https://mlsanity.com/paper/2410.19115/) (2024)
- [GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces](https://mlsanity.com/paper/2311.17977/) (2023)
- [ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI](https://mlsanity.com/paper/2410.00425/) (2024)
- [Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer](https://mlsanity.com/paper/1908.01210/) (2019)
- [AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains](https://mlsanity.com/paper/2212.08333/) (2022)
- [DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos](https://mlsanity.com/paper/2409.02095/) (2024)
- [Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction](https://mlsanity.com/paper/2409.18124/) (2024)
- [StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal](https://mlsanity.com/paper/2406.16864/) (2024)
- [SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis](https://mlsanity.com/paper/1708.01749/) (2017)
- [ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation](https://mlsanity.com/paper/1910.02550/) (2019)
- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [UniScene: Unified Occupancy-centric Driving Scene Generation](https://mlsanity.com/paper/2412.05435/) (2024)
- [Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging](https://mlsanity.com/paper/2503.22236/) (2025)
- [FastDepth: Fast Monocular Depth Estimation on Embedded Systems](https://mlsanity.com/paper/1903.03273/) (2019)
- [Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think](https://mlsanity.com/paper/2409.11355/) (2024)
- [Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation](https://mlsanity.com/paper/2412.14015/) (2024)
- [Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image](https://mlsanity.com/paper/1808.02201/) (2018)
- [SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation](https://mlsanity.com/paper/1810.01849/) (2018)
- [cuRobo: Parallelized Collision-Free Minimum-Jerk Robot Motion Generation](https://mlsanity.com/paper/2310.17274/) (2023)
- [PS-FCN: A Flexible Learning Framework for Photometric Stereo](https://mlsanity.com/paper/1807.08696/) (2018)

## Built on by (most cited first, 10 of 10)

- [Towards Consistent Video Geometry Estimation](https://mlsanity.com/paper/2605.30060/) (2026)
- [TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation](https://mlsanity.com/paper/2602.00839/) (2026)
- [SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification](https://mlsanity.com/paper/2603.19547/) (2026)
- [Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting](https://mlsanity.com/paper/2606.05124/) (2026)
- [OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes](https://mlsanity.com/paper/2608.29881/) (2026)
- [GHOST: Geometry-Guided Hallucination of Opaque Surface Textures](https://mlsanity.com/paper/2607.11118/) (2026)
- [GeoStereo: A Unified Stereo Geometry Estimation Framework for Disparity and Surface Normal](https://mlsanity.com/paper/2607.24024/) (2026)
- [WildShadowRemover: In-the-Wild Video Shadow Removal via Detail-Preserving Video Diffusion Models](https://mlsanity.com/paper/2607.26203/) (2026)
- [GIFT: Geometry-Invariant Fine-Tuning for Non-Lambertian Monocular Depth Estimation](https://mlsanity.com/paper/2608.02068/) (2026)
- [TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation](https://mlsanity.com/paper/2609.06665/) (2026)

## Abstract (arXiv)

Transparent objects remain notoriously hard for perception systems: refraction, reflection and transmission break the assumptions behind stereo, ToF and purely discriminative monocular depth, causing holes and temporally unstable estimates. Our key observation is that modern video diffusion models already synthesize convincing transparent phenomena, suggesting they have internalized the optical rules. We build TransPhy3D, a synthetic video corpus of transparent/reflective scenes: 11k sequences rendered with Blender/Cycles. Scenes are assembled from a curated bank of category-rich static assets and shape-rich procedural assets paired with glass/plastic/metal materials. We render RGB + depth + normals with physically based ray tracing and OptiX denoising. Starting from a large video diffusion model, we learn a video-to-video translator for depth (and normals) via lightweight LoRA adapters. During training we concatenate RGB and (noisy) depth latents in the DiT backbone and co-train on TransPhy3D and existing frame-wise synthetic datasets, yielding temporally consistent predictions for arbitrary-length input videos. The resulting model, DKT, achieves zero-shot SOTA on real and synthetic video benchmarks involving transparency: ClearPose, DREDS (CatKnown/CatNovel), and TransPhy3D-Test. It improves accuracy and temporal consistency over strong image/video baselines, and a normal variant sets the best video normal estimation results on ClearPose. A compact 1.3B version runs at ~0.17 s/frame. Integrated into a grasping stack, DKT's depth boosts success rates across translucent, reflective and diffuse surfaces, outperforming prior estimators. Together, these results support a broader claim: "Diffusion knows transparency." Generative video priors can be repurposed, efficiently and label-free, into robust, temporally coherent perception for challenging real-world manipulation.