# IntrinsicReal: Adapting IntrinsicAnything from Synthetic to Real Objects

arXiv: https://arxiv.org/abs/2509.00777 · HTML: https://mlsanity.com/paper/2509.00777/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 50 references that are in the map.
- First posted on arXiv 31 Aug 2025.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks](https://mlsanity.com/paper/1612.05424/) (2016)
- [MVImgNet: A Large-scale Dataset of Multi-view Images](https://mlsanity.com/paper/2303.06042/) (2023)
- [Image to Image Translation for Domain Adaptation](https://mlsanity.com/paper/1712.00479/) (2017)
- [RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion models](https://mlsanity.com/paper/2405.00666/) (2024)
- [GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB](https://mlsanity.com/paper/1712.01057/) (2017)
- [Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data](https://mlsanity.com/paper/2203.16258/) (2022)
- [CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering](https://mlsanity.com/paper/1808.08601/) (2018)
- [T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks](https://mlsanity.com/paper/1808.01454/) (2018)
- [IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination](https://mlsanity.com/paper/2404.11593/) (2024)
- [Autonomous Overtaking in Gran Turismo Sport Using Curriculum Reinforcement Learning](https://mlsanity.com/paper/2103.14666/) (2021)
- [Learning Non-Lambertian Object Intrinsics across ShapeNet Categories](https://mlsanity.com/paper/1612.08510/) (2016)
- [Curriculum Self-Paced Learning for Cross-Domain Object Detection](https://mlsanity.com/paper/1911.06849/) (2019)
- [LIME: Live Intrinsic Material Estimation](https://mlsanity.com/paper/1801.01075/) (2018)
- [PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection](https://mlsanity.com/paper/2205.11098/) (2022)
- [MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors](https://mlsanity.com/paper/2409.15273/) (2024)
- [Shading Annotations in the Wild](https://mlsanity.com/paper/1705.01156/) (2017)
- [CNN based Learning using Reflection and Retinex Models for Intrinsic Image Decomposition](https://mlsanity.com/paper/1712.01056/) (2017)
- [Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2308.11901/) (2023)
- [Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement](https://mlsanity.com/paper/2003.12649/) (2020)
- [Enhanced Transfer Learning for Autonomous Driving with Systematic Accident Simulation](https://mlsanity.com/paper/2007.12148/) (2020)

## Abstract (arXiv)

Estimating albedo (a.k.a., intrinsic image decomposition) from single RGB images captured in real-world environments (e.g., the MVImgNet dataset) presents a significant challenge due to the absence of paired images and their ground truth albedos. Therefore, while recent methods (e.g., IntrinsicAnything) have achieved breakthroughs by harnessing powerful diffusion priors, they remain predominantly trained on large-scale synthetic datasets (e.g., Objaverse) and applied directly to real-world RGB images, which ignores the large domain gap between synthetic and real-world data and leads to suboptimal generalization performance. In this work, we address this gap by proposing IntrinsicReal, a novel domain adaptation framework that bridges the above-mentioned domain gap for real-world intrinsic image decomposition. Specifically, our IntrinsicReal adapts IntrinsicAnything to the real domain by fine-tuning it using its high-quality output albedos selected by a novel dual pseudo-labeling strategy: i) pseudo-labeling with an absolute confidence threshold on classifier predictions, and ii) pseudo-labeling using the relative preference ranking of classifier predictions for individual input objects. This strategy is inspired by human evaluation, where identifying the highest-quality outputs is straightforward, but absolute scores become less reliable for sub-optimal cases. In these situations, relative comparisons of outputs become more accurate. To implement this, we propose a novel two-phase pipeline that sequentially applies these pseudo-labeling techniques to effectively adapt IntrinsicAnything to the real domain. Experimental results show that our IntrinsicReal significantly outperforms existing methods, achieving state-of-the-art results for albedo estimation on both synthetic and real-world datasets.