A Human-in-the-Loop Deep Learning Framework for Color Reconstruction of Lenticular Films

• URL: http://arxiv.org/abs/2608.02835v2
• Date: Wed, 05 Aug 2026 09:00:12 GMT
• Title: A Human-in-the-Loop Deep Learning Framework for Color Reconstruction of Lenticular Films
• Abstract summary: We propose a human-in-the-loop deep learning framework which is designed for color reconstruction in lenticular films.<n>Our approach introduces an editable, vector-based representation of lenticule boundaries, allowing experts to interactively refine boundary positions.<n>To preserve image details using information solely present in the original silver emulsion, we merge the reconstructed chrominance with the original film scan's luminance.
• Score: 1.2744523252873352
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Historical lenticular films, such as those created with the Kodacolor process, encode color information in a distinctive spatial format. This structure requires specialized techniques for accurate color reconstruction. While recent signal processing approaches like doLCE and deep learning methods like deep-doLCE have advanced automated color recovery, they often fail with cases such as curved lenticules, low-contrast, or badly captured regions. We propose a human-in-the-loop (HITL) deep learning framework which is designed for color reconstruction in lenticular films. Our approach introduces an editable, vector-based representation of lenticule boundaries, allowing experts to interactively refine boundary positions before color extraction and demosaicing. This decoupled architecture enables targeted corrections and iterative fine-tuning, embedding expert knowledge into the detection model and improving robustness across challenging frames. To preserve image details using information solely present in the original silver emulsion, we merge the reconstructed chrominance with the original film scan's luminance. We evaluate our pipeline on a challenging lenticular film sequence where previous automated approaches fail and the reconstructed colors are not suitable for exhibition. In contrast, our HITL approach successfully produces high-quality, exhibitable color reconstructions with preserved texture. This work is the first to combine expert guidance, editable intermediate representations, and texture-preserving post-processing for lenticular film color reconstruction, advancing the state of the art in this field.

Related papers

• DANTE-W: Diffuse Albedo Neural Texturing in the Wild [15.545994699853813]
  We present a framework for recovering texture from unstructured image collections.<n>Our method integrates texture reconstruction with traditional 3D pipelines.<n>We evaluate our approach in reconstructing accurate textures and boosting fidelity.
  arXiv  Detail & Related papers  (2026-06-26T09:45:56Z)
• ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization [34.04054653090656]
  We propose a novel old photo colorization framework based on the generative diffusion model FLUX.<n>We introduce a structure-color decoupling strategy that separates structure preservation from color restoration, enabling accurate colorization of old photos.<n>We also introduce visual semantic prompts, which extract fine-grained semantic information directly from old photos, helping to eliminate the color bias inherent in old photos.
  arXiv  Detail & Related papers  (2026-03-30T08:29:16Z)
• VIRGi: View-dependent Instant Recoloring of 3D Gaussians Splats [53.602701067430075]
  We introduce VIRGi, a novel approach for rapidly editing the color of scenes modeled by 3DGS.<n>By fine-tuning the weights of a single user, the color edits are seamlessly propagated to the entire scene in just two seconds.<n>An exhaustive validation on diverse datasets demonstrates significant quantitative and qualitative advancements over competitors.
  arXiv  Detail & Related papers  (2026-03-03T13:41:17Z)
• InpaintHuman: Reconstructing Occluded Humans with Multi-Scale UV Mapping and Identity-Preserving Diffusion Inpainting [64.42884719282323]
  InpaintHuman is a novel method for generating high-fidelity, complete, and animatable avatars from occluded monocular videos.<n>Our approach employs direct pixel-level supervision to ensure identity fidelity.
  arXiv  Detail & Related papers  (2026-01-05T13:26:02Z)
• DiffTex: Differentiable Texturing for Architectural Proxy Models [63.370581207280004]
  We propose an automated method for generating realistic texture maps for architectural proxy models at the texel level from unordered photographs.<n>Our approach establishes correspondences between texels on a UV map and pixels in the input images, with each texel's color computed as a weighted blend of associated pixel values.
  arXiv  Detail & Related papers  (2025-09-27T14:39:53Z)
• Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes [62.769186261245416]
  We present a novel inverse rendering framework for large urban scenes capable of jointly reconstructing the scene geometry, spatially-varying materials, and HDR lighting from a set of posed RGB images with optional depth. Specifically, we use a neural field to account for the primary rays, and use an explicit mesh (reconstructed from the underlying neural field) for modeling secondary rays that produce higher-order lighting effects such as cast shadows.
  arXiv  Detail & Related papers  (2023-04-06T17:51:54Z)
• RecolorNeRF: Layer Decomposed Radiance Fields for Efficient Color Editing of 3D Scenes [21.284044381058575]
  We present RecolorNeRF, a novel user-friendly color editing approach for neural radiance fields. Our key idea is to decompose the scene into a set of pure-colored layers, forming a palette. To support efficient palette-based editing, the color of each layer needs to be as representative as possible.
  arXiv  Detail & Related papers  (2023-01-19T09:18:06Z)
• PaletteNeRF: Palette-based Appearance Editing of Neural Radiance Fields [60.66412075837952]
  We present PaletteNeRF, a novel method for appearance editing of neural radiance fields (NeRF) based on 3D color decomposition. Our method decomposes the appearance of each 3D point into a linear combination of palette-based bases. We extend our framework with compressed semantic features for semantic-aware appearance editing.
  arXiv  Detail & Related papers  (2022-12-21T00:20:01Z)
• A Deep Learning Approach for Digital ColorReconstruction of Lenticular Films [8.264186103325725]
  Lenticular films emerged in the 1920s and were one of the first technologies that permitted to capture full color information in motion. In this work, we introduce an automated, fully digital pipeline to process the scan of lenticular films and colorize the image. Our method merges deep learning with a model-based approach in order to maximize the performance while making sure that the reconstructed colored images truthfully match the encoded color information.
  arXiv  Detail & Related papers  (2022-02-10T11:08:50Z)
• Image Inpainting with External-internal Learning and Monochromic Bottleneck [39.89676105875726]
  We propose an external-internal inpainting scheme with a monochromic bottleneck that helps image inpainting models remove these artifacts. In the external learning stage, we reconstruct missing structures and details in the monochromic space to reduce the learning dimension. In the internal learning stage, we propose a novel internal color propagation method with progressive learning strategies for consistent color restoration.
  arXiv  Detail & Related papers  (2021-04-19T06:22:10Z)
• Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracing [49.759478460828504]
  Methods combining deep neural network encoders with differentiable rendering have opened up the path for very fast monocular reconstruction of geometry, lighting and reflectance. ray tracing was introduced for monocular face reconstruction within a classic optimization-based framework. We propose a new method that greatly improves reconstruction quality and robustness in general scenes.
  arXiv  Detail & Related papers  (2021-03-29T08:58:10Z)

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.