Lumos3D: A Single-Forward Framework for Low-Light 3D Scene Restoration

• URL: http://arxiv.org/abs/2511.09818v1
• Date: Fri, 14 Nov 2025 01:11:02 GMT
• Title: Lumos3D: A Single-Forward Framework for Low-Light 3D Scene Restoration
• Authors: Hanzhou Liu, Peng Jiang, Jia Huang, Mi Lu,
• Abstract summary: We introduce Lumos3D, a pose-free framework for 3D low-light scene restoration.<n>Built upon a geometry-grounded backbone, Lumos3D reconstructs a normal-light 3D Gaussian representation.<n>Experiments on real-world datasets demonstrate that Lumos3D achieves high- fidelity low-light 3D scene restoration.
• Score: 10.184395697154448
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Restoring 3D scenes captured under low-light con- ditions remains a fundamental yet challenging problem. Most existing approaches depend on precomputed camera poses and scene-specific optimization, which greatly restricts their scala- bility to dynamic real-world environments. To overcome these limitations, we introduce Lumos3D, a generalizable pose-free framework for 3D low-light scene restoration. Trained once on a single dataset, Lumos3D performs inference in a purely feed- forward manner, directly restoring illumination and structure from unposed, low-light multi-view images without any per- scene training or optimization. Built upon a geometry-grounded backbone, Lumos3D reconstructs a normal-light 3D Gaussian representation that restores illumination while faithfully pre- serving structural details. During training, a cross-illumination distillation scheme is employed, where the teacher network is distilled on normal-light ground truth to transfer accurate geometric information, such as depth, to the student model. A dedicated Lumos loss is further introduced to promote photomet- ric consistency within the reconstructed 3D space. Experiments on real-world datasets demonstrate that Lumos3D achieves high- fidelity low-light 3D scene restoration with accurate geometry and strong generalization to unseen cases. Furthermore, the framework naturally extends to handle over-exposure correction, highlighting its versatility for diverse lighting restoration tasks.

Related papers

• R3GW: Relightable 3D Gaussians for Outdoor Scenes in the Wild [23.68389428693905]
  3D Gaussian Splatting (3DGS) has established itself as a leading technique for 3D reconstruction and novel view synthesis of static scenes.<n>We present R3GW, a novel method that learns a relightable 3DGS representation of an outdoor scene captured in the wild.
  arXiv  Detail & Related papers  (2026-03-03T09:40:16Z)
• GR3EN: Generative Relighting for 3D Environments [52.77521698841744]
  We present a method for relighting 3D reconstructions of large room-scale environments.<n>Our approach enables controllable 3D relighting of room-scale scenes by distilling the outputs of a video-to-video relighting diffusion model into a 3D reconstruction.<n>This side-steps the need to solve a difficult inverse rendering problem, and results in a flexible system that can relight 3D reconstructions of complex real-world scenes.
  arXiv  Detail & Related papers  (2026-01-22T19:10:05Z)
• Soft Shadow Diffusion (SSD): Physics-inspired Learning for 3D Computational Periscopy [9.625436987364909]
  Non-line-of-sight (NLOS) imaging reconstructs hidden scenes from indirect measurements.<n>Here, we demonstrate a 3D reconstruction of a hidden scene from an ordinary NLOS photograph.<n>We develop two solutions: A gradient-based optimization method and a physics-inspired neural network approach, which we call Soft Shadow diffusion.
  arXiv  Detail & Related papers  (2026-01-18T04:40:00Z)
• ComGS: Efficient 3D Object-Scene Composition via Surface Octahedral Probes [46.83857963152283]
  Gaussian Splatting (GS) enables immersive rendering, but realistic 3D object-scene composition remains challenging.<n>We propose ComGS, a novel 3D object-scene composition framework.<n>Our method achieves high-quality, real-time rendering at around 28 FPS, produces visually harmonious results with vivid shadows, and requires only 36 seconds for editing.
  arXiv  Detail & Related papers  (2025-10-09T03:10:41Z)
• MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation [19.46962637673285]
  MV-CoLight is a framework for illumination-consistent object compositing in 2D and 3D scenes.<n>We employ a Hilbert curve-based mapping to align 2D image inputs with 3D Gaussian scene representations seamlessly.<n> Experiments demonstrate state-of-the-art harmonized results across standard benchmarks and our dataset.
  arXiv  Detail & Related papers  (2025-05-27T17:53:02Z)
• SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations [44.53106180688135]
  This work takes on the challenge of reconstructing 3D scenes from sparse or single-view inputs.<n>We introduce SpatialCrafter, a framework that leverages the rich knowledge in video diffusion models to generate plausible additional observations.<n>Through a trainable camera encoder and an epipolar attention mechanism for explicit geometric constraints, we achieve precise camera control and 3D consistency.
  arXiv  Detail & Related papers  (2025-05-17T13:05:13Z)
• Lite2Relight: 3D-aware Single Image Portrait Relighting [87.62069509622226]
  Lite2Relight is a novel technique that can predict 3D consistent head poses of portraits. By utilizing a pre-trained geometry-aware encoder and a feature alignment module, we map input images into a relightable 3D space. This includes producing 3D-consistent results of the full head, including hair, eyes, and expressions.
  arXiv  Detail & Related papers  (2024-07-15T07:16:11Z)
• 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)
• 3D Scene Creation and Rendering via Rough Meshes: A Lighting Transfer Avenue [49.62477229140788]
  This paper studies how to flexibly integrate reconstructed 3D models into practical 3D modeling pipelines such as 3D scene creation and rendering. We propose a lighting transfer network (LighTNet) to bridge NFR and PBR, such that they can benefit from each other.
  arXiv  Detail & Related papers  (2022-11-27T13:31:00Z)
• PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes [84.66946637534089]
  PhotoScene is a framework that takes input image(s) of a scene and builds a photorealistic digital twin with high-quality materials and similar lighting. We model scene materials using procedural material graphs; such graphs represent photorealistic and resolution-independent materials. We evaluate our technique on objects and layout reconstructions from ScanNet, SUN RGB-D and stock photographs, and demonstrate that our method reconstructs high-quality, fully relightable 3D scenes.
  arXiv  Detail & Related papers  (2022-07-02T06:52:44Z)
• Towards Non-Line-of-Sight Photography [48.491977359971855]
  Non-line-of-sight (NLOS) imaging is based on capturing the multi-bounce indirect reflections from the hidden objects. Active NLOS imaging systems rely on the capture of the time of flight of light through the scene. We propose a new problem formulation, called NLOS photography, to specifically address this deficiency.
  arXiv  Detail & Related papers  (2021-09-16T08:07:13Z)
• Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting [149.1673041605155]
  We address the problem of jointly estimating albedo, normals, depth and 3D spatially-varying lighting from a single image. Most existing methods formulate the task as image-to-image translation, ignoring the 3D properties of the scene. We propose a unified, learning-based inverse framework that formulates 3D spatially-varying lighting.
  arXiv  Detail & Related papers  (2021-09-13T15:29:03Z)

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.