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

• URL: http://arxiv.org/abs/2604.02787v1
• Date: Fri, 03 Apr 2026 06:54:52 GMT
• Title: LumaFlux: Lifting 8-Bit Worlds to HDR Reality with Physically-Guided Diffusion Transformers
• Abstract summary: We introduce LumaFlux, a first physically and perceptually guided transformer for SDR-to-reconstruction.<n>Across benchmarks, LumaFlux outperforms state-of-the-art baselines, achieving superior luminance reconstruction and perceptual color fidelity.
• Score: 33.647308897653396
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Bio-SFT: Asymmetric Cortical Guidance and Retinal Adaptation for Robust HDR Reconstruction [61.07381300333128]
  Extreme luminance variation and severe quantization in dark regions make accurate reconstruction challenging.<n>Bio-SFT is a bio-inspired spiking frequency transformer for single-image HDR reconstruction.<n>Experiments on HDRTV1K show that Bio-SFT consistently improves HDR-VDP-3 and $E_ITP$ while reducing artifact propagation in symmetric guidance pipelines.
  arXiv  Detail & Related papers  (2026-07-20T01:07:54Z)
• ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction [60.873186669266836]
  Single-image HDR reconstruction aims to recover high dynamic range radiance from a single low dynamic range (LDR) input, but remains highly ill-posed due to detail saturation in over-exposed regions and noise amplification in under-exposed areas.<n>We propose ExpoCM, a novel one-step generative HDR reconstruction framework that reformulates HDR reconstruction as a Probability Flow ODE (PF-ODE) and constructs exposure-aware consistency trajectories via exposure-dependent perturbations.<n>Experiments on the HDR-REAL, HDR-EYE, and AIM2025 benchmarks demonstrate that ExpoCM achieves state-of-the-art fidelity
  arXiv  Detail & Related papers  (2026-05-04T11:06:49Z)
• High-Speed Full-Color HDR Imaging via Unwrapping Modulo-Encoded Spike Streams [83.83721273785281]
  We present a complete modulo-based HDR imaging system that enables high-speed, full-color HDR acquisition.<n>At the core of our approach is an exposure-decoupled formulation of modulo imaging that allows multiple measurements to be interleaved in time.<n>To validate the practical viability of our system, we demonstrate a proof-of-concept hardware implementation based on modulo-encoded spike streams.
  arXiv  Detail & Related papers  (2026-04-16T05:20:38Z)
• DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models [35.73610036182625]
  Diff is a framework that formulates LDR-to-generative conversion within the latent space of a video diffusion model.<n>Our framework further enables controllable LDR-to-video conversion guided by text or reference images.
  arXiv  Detail & Related papers  (2026-04-07T17:56:18Z)
• Physically Inspired Gaussian Splatting for HDR Novel View Synthesis [40.99906396910274]
  High dynamic range novel view synthesis (biased-NVS) reconstructs scenes with dynamic details by fusing multi-exposure low dynamic range (LDR) views.<n>Implicitly HDR content by constraining tone-mapped results fails in correcting abnormal HDR values, and results in limited gradients for Gaussians in under/over-exposed regions.<n>We introduce Phys-GS, a physically inspired HDR-NVS framework that models scene appearance via intrinsic reflectance and adjustable ambient illumination.
  arXiv  Detail & Related papers  (2026-03-30T04:27:39Z)
• X2HDR: HDR Image Generation in a Perceptually Uniform Space [37.83280929526874]
  High-dynamic-range formats and displays are becoming increasingly prevalent, yet state-of-the-art image generators are limited to low-dynamic-range (LDR) output.<n>We show that existing pretrained diffusion models can be easily adapted to HDR generation without retraining from scratch.
  arXiv  Detail & Related papers  (2026-02-04T17:59:51Z)
• GMODiff: One-Step Gain Map Refinement with Diffusion Priors for HDR Reconstruction [48.881484713994496]
  We introduce GMODiff, a gain map-driven one-step diffusion framework for multi-exposure HDR reconstruction.<n>Our GMO performs favorably against several state-of-the-art methods and is 100 faster than previous LDM-based methods.
  arXiv  Detail & Related papers  (2025-12-18T09:50:25Z)
• Reconstructing 3D Scenes in Native High Dynamic Range [82.90064638813185]
  We present the first method for 3D scene reconstruction that directly models native HDR observations.<n>We propose bf Native High dynamic range 3D Gaussian Splatting (NH-3DGS), which preserves the full dynamic range throughout the reconstruction pipeline.<n>We demonstrate on both synthetic and real multi-view HDR datasets that NH-3DGS significantly outperforms existing methods in reconstruction quality and dynamic range preservation.
  arXiv  Detail & Related papers  (2025-11-17T02:33:31Z)
• LEDiff: Latent Exposure Diffusion for HDR Generation [11.669442066168244]
  LEDiff is a method that enables a generative model with HDR content generation through latent space exposure fusion techniques.<n>It also functions as an LDR-to- fusion converter, expanding the dynamic range of existing low-dynamic range images.
  arXiv  Detail & Related papers  (2024-12-19T02:15:55Z)
• HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting [76.5908492298286]
  Existing HDR NVS methods are mainly based on NeRF. They suffer from long training time and slow inference speed. We propose a new framework, High Dynamic Range Gaussian Splatting (-GS)
  arXiv  Detail & Related papers  (2024-05-24T00:46:58Z)
• Generating Content for HDR Deghosting from Frequency View [56.103761824603644]
  Recent Diffusion Models (DMs) have been introduced in HDR imaging field. DMs require extensive iterations with large models to estimate entire images. We propose the Low-Frequency aware Diffusion (LF-Diff) model for ghost-free HDR imaging.
  arXiv  Detail & Related papers  (2024-04-01T01:32:11Z)
• LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction [20.911738532410766]
  We propose an end-to-end HDR video composition framework, which aligns LDR frames in feature space and then merges aligned features into an HDR frame. In training, we adopt a temporal loss, in addition to frame reconstruction losses, to enhance temporal consistency and thus reduce flickering.
  arXiv  Detail & Related papers  (2023-08-22T01:43:00Z)
• Efficient HDR Reconstruction from Real-World Raw Images [16.54071503000866]
  High-definition screens on edge devices stimulate a strong demand for efficient high dynamic range ( HDR) algorithms. Many existing HDR methods either deliver unsatisfactory results or consume too much computational and memory resources. In this work, we discover an excellent opportunity for HDR reconstructing directly from raw images and investigating novel neural network structures.
  arXiv  Detail & Related papers  (2023-06-17T10:10:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.