# LumaFlux: Lifting 8-Bit Worlds to HDR Reality with Physically-Guided Diffusion Transformers

arXiv: https://arxiv.org/abs/2604.02787 · HTML: https://mlsanity.com/paper/2604.02787/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 28 of 28)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Neural Spline Flows](https://mlsanity.com/paper/1906.04032/) (2019)
- [Rectified Flow: A Marginal Preserving Approach to Optimal Transport](https://mlsanity.com/paper/2209.14577/) (2022)
- [HDR image reconstruction from a single exposure using deep CNNs](https://mlsanity.com/paper/1710.07480/) (2017)
- [Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline](https://mlsanity.com/paper/2004.01179/) (2020)
- [Dynamic Diffusion Transformer](https://mlsanity.com/paper/2410.03456/) (2024)
- [FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution](https://mlsanity.com/paper/2510.12747/) (2025)
- [HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular content](https://mlsanity.com/paper/2304.13625/) (2023)
- [Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applications](https://mlsanity.com/paper/1904.11176/) (2019)
- [JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video](https://mlsanity.com/paper/1909.04391/) (2019)
- [A New Journey from SDRTV to HDRTV](https://mlsanity.com/paper/2108.07978/) (2021)
- [LEDiff: Latent Exposure Diffusion for HDR Generation](https://mlsanity.com/paper/2412.14456/) (2024)
- [Rectified-CFG++ for Flow Based Models](https://mlsanity.com/paper/2510.07631/) (2025)
- [Generating Content for HDR Deghosting from Frequency View](https://mlsanity.com/paper/2404.00849/) (2024)
- [SDRTV-to-HDRTV via Hierarchical Dynamic Context Feature Mapping](https://mlsanity.com/paper/2207.00319/) (2022)
- [Learning a Practical SDR-to-HDRTV Up-conversion using New Dataset and Degradation Models](https://mlsanity.com/paper/2303.13031/) (2023)
- [HIDRO-VQA: High Dynamic Range Oracle for Video Quality Assessment](https://mlsanity.com/paper/2311.11059/) (2023)
- [Subjective Quality Assessment of Compressed Tone-Mapped High Dynamic Range Videos](https://mlsanity.com/paper/2403.15061/) (2024)
- [CHUG: Crowdsourced User-Generated HDR Video Quality Dataset](https://mlsanity.com/paper/2510.09879/) (2025)

## Abstract (arXiv)

The rapid adoption of HDR-capable devices has created a pressing need to convert the 8-bit Standard Dynamic Range (SDR) content into perceptually and physically accurate 10-bit High Dynamic Range (HDR). Existing inverse tone-mapping (ITM) methods often rely on fixed tone-mapping operators that struggle to generalize to real-world degradations, stylistic variations, and camera pipelines, frequently producing clipped highlights, desaturated colors, or unstable tone reproduction. We introduce LumaFlux, a first physically and perceptually guided diffusion transformer (DiT) for SDR-to-HDR reconstruction by adapting a large pretrained DiT. Our LumaFlux introduces (1) a Physically-Guided Adaptation (PGA) module that injects luminance, spatial descriptors, and frequency cues into attention through low-rank residuals; (2) a Perceptual Cross-Modulation (PCM) layer that stabilizes chroma and texture via FiLM conditioning from vision encoder features; and (3) an HDR Residual Coupler that fuses physical and perceptual signals under a timestep- and layer-adaptive modulation schedule. Finally, a lightweight Rational-Quadratic Spline decoder reconstructs smooth, interpretable tone fields for highlight and exposure expansion, enhancing the output of the VAE decoder to generate HDR. To enable robust HDR learning, we curate the first large-scale SDR-HDR training corpus. For fair and reproducible comparison, we further establish a new evaluation benchmark, comprising HDR references and corresponding expert-graded SDR versions. Across benchmarks, LumaFlux outperforms state-of-the-art baselines, achieving superior luminance reconstruction and perceptual color fidelity with minimal additional parameters.