Toward Real-World Adoption of Portrait Relighting via Hybrid Domain Knowledge Fusion

• URL: http://arxiv.org/abs/2604.23094v1
• Date: Sat, 25 Apr 2026 01:16:11 GMT
• Title: Toward Real-World Adoption of Portrait Relighting via Hybrid Domain Knowledge Fusion
• Abstract summary: We present a paradigm that fuses the specialized strengths of synthetic, One-Light-at-A-Time (OLAT), and real-world datasets into a compact model.<n>Our approach features specialized prior models hardened by domain-aware adaptation, followed by augmented knowledge distillation into a lightweight student model.<n>We construct a massive, high-fidelity synthetic dataset with diverse ground-truth intrinsics to support our training pipeline.
• Score: 17.59278811759214
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The real-world adoption of portrait relighting is hindered by dataset domain gaps, camera sensitivity, and computational costs. We address these challenges with Hybrid Domain Knowledge Fusion, a paradigm that fuses the specialized strengths of synthetic, One-Light-at-A-Time (OLAT), and real-world datasets into a compact model. Our approach features specialized prior models hardened by domain-aware adaptation, followed by augmented knowledge distillation into a lightweight student model with multi-domain expertise. Our method demonstrates a 6x to 240x inference speedup while maintaining state-of-the-art (SOTA) visual quality in the experiments. Additionally, we construct a massive, high-fidelity synthetic dataset with diverse ground-truth intrinsics to support our training pipeline.

Related papers

• The Power of Light: Improving Synthetic-to-Real Domain Adaptation through Physically-Based Indirect Illumination [0.0]
  This paper presents a systematic study analyzing the impact of lighting configurations and background complexity on object detection performance.<n>Through 18 controlled experiments utilizing a state-of-the-art YOLOv12 framework, we demonstrate that complex, indirect lighting configurations paired with domain-relevant background variability significantly increase visual cue richness.<n>Our findings show that avoiding direct specular peaks preserves crucial surface textures, mitigates the domain gap, reduces false positives, and accelerates model convergence compared to using conventional direct-light synthetic data.
  arXiv  Detail & Related papers  (2026-06-21T16:21:34Z)
• WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting [1.4145309506833206]
  We introduce WildRelight, the first in-the-wild dataset specifically created for evaluating single-image relighting models.<n>We show that the dataset allows synthetic models to align with real-world statistics on-the-fly, transforming the intractable sim-to-real challenge into a tractable self-supervised task.
  arXiv  Detail & Related papers  (2026-05-12T07:53:27Z)
• Addressing the Depth-of-Field Constraint: A New Paradigm for High Resolution Multi-Focus Image Fusion [4.001780301402233]
  Multi-focus image fusion (MFIF) addresses the depth-of-field (DOF) limitations of optical lenses.<n>We propose VAEEDOF, a novel MFIF method that uses a distilled variational autoencoder for high-fidelity, efficient image reconstruction.<n>Our method achieves state-of-the-art results, generating seamless artifact-free fused images and bridging the gap between synthetic and real-world scenarios.
  arXiv  Detail & Related papers  (2025-10-22T13:32:04Z)
• LuxDiT: Lighting Estimation with Video Diffusion Transformer [66.60450792095901]
  Estimating scene lighting from a single image or video remains a longstanding challenge in computer vision and graphics.<n>We propose LuxDiT, a novel data-driven approach that fine-tunes a video diffusion transformer to generate HDR environment maps conditioned on visual input.
  arXiv  Detail & Related papers  (2025-09-03T19:59:20Z)
• UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting [85.27994475113056]
  We introduce a general-purpose approach that jointly estimates albedo and synthesizes relit outputs in a single pass.<n>Our model demonstrates strong generalization across diverse domains and surpasses previous methods in both visual fidelity and temporal consistency.
  arXiv  Detail & Related papers  (2025-06-18T17:56:45Z)
• Boosting Zero-shot Stereo Matching using Large-scale Mixed Images Sources in the Real World [8.56549004133167]
  Stereo matching methods rely on dense pixel-wise ground truth labels.<n>The scarcity of labeled data and domain gaps between synthetic and real-world images pose notable challenges.<n>We propose a novel framework, textbfBooSTer, that leverages both vision foundation models and large-scale mixed image sources.
  arXiv  Detail & Related papers  (2025-05-13T14:24:38Z)
• IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations [64.07859467542664]
  Capturing geometric and material information from images remains a fundamental challenge in computer vision and graphics.<n>Traditional optimization-based methods often require hours of computational time to reconstruct geometry, material properties, and environmental lighting from dense multi-view inputs.<n>We introduce IDArb, a diffusion-based model designed to perform intrinsic decomposition on an arbitrary number of images under varying illuminations.
  arXiv  Detail & Related papers  (2024-12-16T18:52:56Z)
• A Dual Domain Multi-exposure Image Fusion Network based on the Spatial-Frequency Integration [57.14745782076976]
  Multi-exposure image fusion aims to generate a single high-dynamic image by integrating images with different exposures. We propose a novelty perspective on multi-exposure image fusion via the Spatial-Frequency Integration Framework, named MEF-SFI. Our method achieves visual-appealing fusion results against state-of-the-art multi-exposure image fusion approaches.
  arXiv  Detail & Related papers  (2023-12-17T04:45:15Z)
• TensoIR: Tensorial Inverse Rendering [51.57268311847087]
  TensoIR is a novel inverse rendering approach based on tensor factorization and neural fields. TensoRF is a state-of-the-art approach for radiance field modeling.
  arXiv  Detail & Related papers  (2023-04-24T21:39:13Z)
• Rethinking Blur Synthesis for Deep Real-World Image Deblurring [4.00114307523959]
  We propose a novel realistic blur synthesis pipeline to simulate the camera imaging process. We develop an effective deblurring model that captures non-local dependencies and local context in the feature domain simultaneously. A comprehensive experiment on three real-world datasets shows that the proposed deblurring model performs better than state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-09-28T06:50:16Z)
• Partially fake it till you make it: mixing real and fake thermal images for improved object detection [29.13557322147509]
  We show the performance of the proposed system in the context of object detection in thermal videos. Our single-modality detector achieves state-of-the-art results on the FLIR ADAS dataset.
  arXiv  Detail & Related papers  (2021-06-25T12:56:09Z)
• Light Field Reconstruction via Deep Adaptive Fusion of Hybrid Lenses [67.01164492518481]
  This paper explores the problem of reconstructing high-resolution light field (LF) images from hybrid lenses. We propose a novel end-to-end learning-based approach, which can comprehensively utilize the specific characteristics of the input. Our framework could potentially decrease the cost of high-resolution LF data acquisition and benefit LF data storage and transmission.
  arXiv  Detail & Related papers  (2021-02-14T06:44:47Z)
• DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization [27.294822556484345]
  Long-term visual localization under changing environments is a challenging problem in autonomous driving and mobile robotics. We propose a novel multi-task architecture to fuse the geometric and semantic information into the multi-scale latent embedding representation for visual place recognition.
  arXiv  Detail & Related papers  (2020-10-01T17:44:25Z)

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.