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

Shreshth Saini; Hakan Gedik; Neil Birkbeck; Yilin Wang; Balu Adsumilli; Alan C. Bovik

cs.CVApr 3, 2026

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

Authors: Shreshth Saini, Hakan Gedik, Neil Birkbeck, Yilin Wang, Balu Adsumilli, Alan C. Bovik

Organizations: The University of Texas at Austin · Google, Inc.

Abstract

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.

Figures & tables

Figure 1: We present LumaFlux , a universal Inverse Tone Mapping (ITM) framework that expands dynamic range and color-gamut from 8 bit BT.709 SDR to 10 bit BT.2020 HDR with PQ encoding (i.e. SDRTV-to-HDRTV) of real-world LQ SDR videos. Figure shows examples from Luma-Eval benchmark. Each pair illustrates the SDR $\!\rightarrow$ HDR conversion result for one representative frame. LumaFlux restores a substantially broader dynamic range and corrects the color saturation lost during tone-mapping compression, recovering both diffuse texture and specular highlight detail.

Figure 2: Architectural Paradigms. (Left) Baseline Diffusion Transformer (DiT) architecture, where the backbone can be directly fine-tuned via LoRA or full-weight updates. Such adaptation often overfits small HDR datasets and leads to texture hallucination or unstable luminance restoration. (Right) The proposed LumaFlux introduces lightweight, physically interpretable modules- PGA , PCM , and the HDR Residual Coupler , inserted into the frozen MM-DiT backbone. These modules enable prompt-free, physically guided adaptation by modulating attention and MLP activations with luminance, frequency, and perceptual cues. This preserves the pretrained generative prior while allowing accurate ITM with only a few trainable parameters. (Best viewed zoomed in)

Figure 3: LumaFlux Overview. SDR input is split into physical ( $T_{\text{phys}}$ ) and perceptual ( $T_{\text{perc}}$ ) streams. With timestep/layer conditioning $\Psi(t,\ell)$ , In each Luma-MMDiT block (see Fig. 2 ), PGA injects luminance and spectrum aware LoRA updates into attention, PCM applies FiLM ( Perez et al., 2018 ) to modulate normalized features, and an HDR Residual Coupler fuses both cues. A frozen VAE decoder with an RQS tone-field head reconstruct HDR in PQ/BT.2020.

Method	HDRTV1K				HDRTV4K				Luma-Eval
Method	PSNR $\uparrow$	SSIM $\uparrow$	HDR-VDP3 $\uparrow$	$\Delta E_{\mathrm{ITP}}\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	HDR-VDP3 $\uparrow$	$\Delta E_{\mathrm{ITP}}\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	HDR-VDP3 $\uparrow$	$\Delta E_{\mathrm{ITP}}\downarrow$
HDRTVNet++ ( Chen et al., 2021 )	38.36	0.973	8.75	8.28	30.82	0.881	8.12	7.85	36.54	0.901	8.22	7.35
ICTCPNet ( Huang et al., 2023 )	36.59	0.922	8.57	7.79	33.12	0.977	8.90	6.75	34.45	0.919	8.74	6.93
HDRTVDM ( Guo et al., 2023 )	36.98	0.971	8.55	10.84	30.15	0.886	7.90	9.95	35.10	0.903	8.24	9.44
HDCFM ( He et al., 2022 )	38.42	0.973	8.52	7.83	33.25	0.908	8.20	7.42	36.78	0.915	8.29	7.20
Deep SR-ITM ( Kim et al., 2019b )	37.10	0.969	8.23	9.24	26.59	0.812	6.92	8.88	33.21	0.875	7.41	8.41

Table 1: Quantitative comparison across benchmarks. We compare LumaFlux with CNN-based and generative methods. Metrics are computed in PU21 space for luminance ( PSNR , SSIM ), HDR domain ( HDR-VDP3 ), and perceptual color (

\mathbf{\Delta E_{\mathrm{ITP}}}

, lower is better). LumaFlux achieves the best overall performance across datasets, consistently improving both dynamic range and colorimetric fidelity. Best results are in bold , second best are underlined .

TMO / Degradation	PSNR $\uparrow$	PSNR(Y) $\uparrow$	$\Delta E_{\mathrm{ITP}}\downarrow$	HDR-VDP3 $\uparrow$	HDR-LPIPS $\downarrow$	FR-HIDROVQA $\uparrow$
OCIOv2	37.85	38.94	5.41	9.12	0.078	82.6
2446c+GM	38.31	39.12	5.18	9.27	0.071	84.1
HC+GM	37.23	38.15	5.66	8.95	0.083	80.4
2446a	36.91	37.62	5.97	8.72	0.087	79.6
Reinhard	35.88	36.42	6.45	8.31	0.091	78.3
YouTube LogC	35.12	35.88	6.81	8.05	0.094	77.9

Table 2: Luma-Eval breakdown by TMO. Results show generalization of LumaFlux across SDR degradations.

Variant	PSNR $\uparrow$	PSNR(Y) $\uparrow$	$\Delta E_{\mathrm{ITP}}\downarrow$	HDR-VDP3 $\uparrow$	HDR-LPIPS $\downarrow$	FR-HIDROVQA $\uparrow$
Flux + LoRA only	33.42	34.28	8.58	7.82	0.136	72.9
+ PGA (no spectral)	34.94	35.81	7.62	8.18	0.122	75.2
+ PGA (with spectral gating)	35.18	36.02	7.31	8.29	0.116	76.3
+ PCM (SigLIP FiLM)	35.89	36.73	6.78	8.46	0.107	78.6
+ RQS (linear)	35.72	36.54	6.85	8.41	0.108	78.0
+ RQS (monotone spline)	35.98	36.84	6.09	8.61	0.087	80.8

Table 3: Ablations for LumaFlux. Highest performance boost arises from PGA, Spectral gating improves highlight roll-off and structure preservation. Adding PCM yields modest chroma stabilization, while RQS (linear) causes over-contrast and banding. The final RQS (monotone spline) restores perceptual smoothness and broadens effective dynamic range.

Method	Brightness $\uparrow$	Color $\uparrow$	Overall $\uparrow$
BT.2446c	2.8	2.9	2.7
HDRTVNet++	3.5	3.6	3.5
LEDiff	3.1	4.0	4.0
PromptIR	3.2	3.8	3.6
LumaFlux (ours)	3.8	4.5	4.2

Table 4: User study (10 raters, 10 clips). Mean Opinion Scores (MOS, 1–5) on perceived brightness, color naturalness, and overall HDR realism.

Panel of Figure 8 — Algorithm 1 SDR $\!\rightarrow$ HDR conversion using LumaFlux

	Expert SDR				BT.2446c SDR
Method	PSNR	$\Delta E_{\mathrm{ITP}}$	HDR - VDP3	HDR - LPIPS	PSNR	$\Delta E_{\mathrm{ITP}}$	HDR - VDP3	HDR - LPIPS
LEDiff	35.12	6.81	8.05	0.094	35.88	6.45	8.31	0.091
PromptIR	36.48	5.89	8.64	0.086	37.23	5.66	8.95	0.083
LumaFlux	37.11	5.53	9.03	0.079	38.31	5.18	9.27	0.071

Table 5: Per-family LIVE - TMHDR - Eval . Expert SDR values come from the “Expert Graded SDR” row in Table 2; BT.2446c SDR values come from the “2446c+GM” row.

Split	#Vid.	Peak	Notes
Train (HIDROVQA)	300	1000	controlled HDR
Train (HDR - UGC - 44K)	$\sim$ 3000	1000	diverse UGC
Train (LIVE - TMHDR)	30	1000	held-out HDR
Eval (HDRTV1K)	std.	1000	synthetic TM
Eval (HDRTV4K)	std.	1000	real+synthetic
Eval (LIVE - TMHDR - Eval)	10	1000	expert+synthetic SDR

Table 6: Unified PQ BT.2020 normalization and peak luminance across all splits.

HDR Imaging

High dynamic range imaging captures or reconstructs scene brightness beyond standard images, preserving detail in shadows and highlights.

See all 47 papers

Aug 6, 2026

Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping

We propose DOME-HDR, a dual-output multi-exposure HDR reconstruction framework that jointly produces a perceptually balanced SDR image and a consistent HDR image via gain map inverse tone mapping. Given three bracketed LDR inputs, DOME-HDR first synthesizes a base SDR using a LoRA-adapted latent diffusion model. A dual cross-attention fusion module injects complementary structural and color cues from the under- and over-exposed images while anchoring on the mid exposure for stability. The synthesized SDR then guides HPGM, our HDR Prior-guided Gain Map network, to predict a spatially varying gain map for reliable dynamic-range expansion. We evaluate on Kalantari, Tel, and Challenge123 using both full-reference and no-reference metrics, where DOME-HDR achieves state-of-the-art HDR reconstruction quality; ablations further confirm the effectiveness of dual cross-attention and SDR-guided gain map estimation.

Jinho Kim, Jinwoo Kim, Seon Joo Kim

Yonsei University, Republic of Korea

HDR Imaging Multi-Exposure Image Fusion

Ask PDF

Dec 18, 2025

GMODiff: One-Step Gain Map Refinement with Diffusion Priors for HDR Reconstruction

Pre-trained Latent Diffusion Models (LDMs) have recently shown strong perceptual priors for low-level vision tasks, making them a promising direction for multi-exposure High Dynamic Range (HDR) reconstruction. However, directly applying LDMs to HDR remains challenging due to: (1) limited dynamic-range representation caused by 8-bit latent compression, (2) high inference cost from multi-step denoising, and (3) content hallucination inherent to their generative nature. To address these challenges, we introduce GMODiff, a gain map-driven one-step diffusion framework for multi-exposure HDR reconstruction. Instead of reconstructing full HDR content, we reformulate HDR reconstruction as a degradation-aware Gain Map (GM) refinement problem, where the GM encodes the extended dynamic range while retaining the same bit depth as LDR images. We initialize the denoising process from an informative regression-based estimate rather than pure noise, allowing the model to generate high-quality GMs in a single denoising step. Furthermore, recognizing that regression-based models excel in content fidelity while LDMs favor perceptual quality, we leverage regression priors to guide both the denoising process and latent decoding of the LDM, suppressing hallucinations while preserving structural accuracy. Extensive experiments demonstrate that GMODiff performs favorably against several state-of-the-art methods and is 100x faster than previous LDM-based methods. Code is available at https://github.com/gbymat/GMODiff.

Tao Hu, Weiyu Zhou, Yanjie Tu +4

Northwestern Polytechnical University, Xi’an 710072, China · Xi’an University of Architecture and Technology, Xi’an 710055, China · The Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen 518057, China

Diffusion Models for Image Restoration Latent Diffusion Models HDR Imaging Image Reconstruction

Ask PDF

Apr 7, 2026

DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models

Most digital videos are stored in 8-bit low dynamic range (LDR) formats, where much of the original high dynamic range (HDR) scene radiance is lost due to saturation and quantization. This loss of highlight and shadow detail precludes mapping accurate luminance to HDR displays and limits meaningful re-exposure in post-production workflows. Although techniques have been proposed to convert LDR images to HDR through dynamic range expansion, they struggle to restore realistic detail in the over- and underexposed regions. To address this, we present DiffHDR, a framework that formulates LDR-to-HDR conversion as a generative radiance inpainting task within the latent space of a video diffusion model. By operating in Log-Gamma color space, DiffHDR leverages spatio-temporal generative priors from a pretrained video diffusion model to synthesize plausible HDR radiance in over- and underexposed regions while recovering the continuous scene radiance of the quantized pixels. Our framework further enables controllable LDR-to-HDR video conversion guided by text prompts or reference images. To address the scarcity of paired HDR video data, we develop a pipeline that synthesizes high-quality HDR video training data from static HDRI maps. Extensive experiments demonstrate that DiffHDR significantly outperforms state-of-the-art approaches in radiance fidelity and temporal stability, producing realistic HDR videos with considerable latitude for re-exposure.

Zhengming Yu, Li Ma, Mingming He +11

Texas A&M University · Eyeline Labs · Netflix

HDR Imaging HDR Video Reconstruction

Ask PDF

Abstract

HDR Imaging

Explore similar work

Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping

GMODiff: One-Step Gain Map Refinement with Diffusion Priors for HDR Reconstruction

DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models