The Power of Light: Improving Synthetic-to-Real Domain Adaptation through Physically-Based Indirect Illumination

• URL: http://arxiv.org/abs/2606.22574v1
• Date: Sun, 21 Jun 2026 16:21:34 GMT
• Title: The Power of Light: Improving Synthetic-to-Real Domain Adaptation through Physically-Based Indirect Illumination
• Abstract summary: 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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While synthetic data generation resolves the manual labeling bottleneck in computer vision, minimizing the syn-to-real domain gap requires optimizing rendering variables. This paper presents a systematic study analyzing the impact of lighting configurations and background complexity on object detection performance. We introduce SmartSDG, an automated, reproducible pipeline built on NVIDIA Isaac Sim using Physically-Based Shading (PBS), alongside ILLUM\_INTRUCK, a new multi-object industrial benchmark dataset. 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. Our quantitative 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. Ultimately, we provide actionable virtual scene design guidelines to maximize object detection robustness in industrial automation.

Related papers

• Metric-Guided Synthetic Image Data Rendering for Deep Learning compatible with Agentic AI [3.1193133788500824]
  Deep learning vision for scientific applications requires collecting and annotating large datasets in a laborious, expensive and error-prone process.<n>We present GraNatPy, Python package with metrics to guide improvement of rendered scene.<n>We show that increase in realism, diversity and size of rendered dataset correlates with improved visual perception of the scene and higher zero-shot performance of an object detection model.
  arXiv  Detail & Related papers  (2026-07-14T15:22:26Z)
• Texture-Shape Bias Balancing for Robust Synthetic-to-Real Semantic Segmentation in Automotive NIR Imagery [6.537821116235228]
  We present the first systematic study on synthetic to real domain adaptation for semantic segmentation in NIR images in the automotive domain.<n>We propose a generative augmentation framework that transforms synthetic images into realistic NIR-style variants.<n>Experiments show that balancing inductive bias during training leads to noticeably more robust semantic segmentation.
  arXiv  Detail & Related papers  (2026-06-13T03:01:10Z)
• Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data [53.040873127309766]
  We propose a token disentanglement process within the transformer architecture, enhancing feature separation and ensuring more effective learning.<n>Our method outperforms existing models on both in-dataset and cross-dataset evaluations.
  arXiv  Detail & Related papers  (2025-09-08T17:58:06Z)
• Geometry-Aware Global Feature Aggregation for Real-Time Indirect Illumination [16.592953713673506]
  We present a learning-based estimator to predict diffuse indirect illumination in screen space.<n>It is combined with direct illumination to synthesize globally-illuminated high dynamic range results.<n>Our approach excels at handling complex lighting such as varying-colored lighting and environment lighting.
  arXiv  Detail & Related papers  (2025-08-12T10:36:03Z)
• How Real is CARLAs Dynamic Vision Sensor? A Study on the Sim-to-Real Gap in Traffic Object Detection [0.0]
  Event cameras are well-suited for real-time object detection at traffic intersections.<n>The development of robust event-based detection models is hindered by the limited availability of annotated real-world datasets.<n>This study offers the first quantifiable analysis of the sim-to-real gap in event-based object detection using CARLAs DVS.
  arXiv  Detail & Related papers  (2025-06-16T17:27:43Z)
• How Important are Data Augmentations to Close the Domain Gap for Object Detection in Orbit? [15.550663626482903]
  We investigate the efficacy of data augmentations to close the domain gap in spaceborne computer vision. We propose two novel data augmentations specifically developed to emulate the visual effects observed in orbital imagery.
  arXiv  Detail & Related papers  (2024-10-21T08:24:46Z)
• Learning to Simulate Realistic LiDARs [66.7519667383175]
  We introduce a pipeline for data-driven simulation of a realistic LiDAR sensor. We show that our model can learn to encode realistic effects such as dropped points on transparent surfaces. We use our technique to learn models of two distinct LiDAR sensors and use them to improve simulated LiDAR data accordingly.
  arXiv  Detail & Related papers  (2022-09-22T13:12:54Z)
• Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection [84.52197307286681]
  We propose a novel multitask auto encoding transformation (MAET) model to enhance object detection in a dark environment. In a self-supervision manner, the MAET learns the intrinsic visual structure by encoding and decoding the realistic illumination-degrading transformation. We have achieved the state-of-the-art performance using synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2022-05-06T16:27:14Z)
• Cycle and Semantic Consistent Adversarial Domain Adaptation for Reducing Simulation-to-Real Domain Shift in LiDAR Bird's Eye View [110.83289076967895]
  We present a BEV domain adaptation method based on CycleGAN that uses prior semantic classification in order to preserve the information of small objects of interest during the domain adaptation process. The quality of the generated BEVs has been evaluated using a state-of-the-art 3D object detection framework at KITTI 3D Object Detection Benchmark.
  arXiv  Detail & Related papers  (2021-04-22T12:47:37Z)
• Neural BRDF Representation and Importance Sampling [79.84316447473873]
  We present a compact neural network-based representation of reflectance BRDF data. We encode BRDFs as lightweight networks, and propose a training scheme with adaptive angular sampling. We evaluate encoding results on isotropic and anisotropic BRDFs from multiple real-world datasets.
  arXiv  Detail & Related papers  (2021-02-11T12:00:24Z)
• Object-based Illumination Estimation with Rendering-aware Neural Networks [56.01734918693844]
  We present a scheme for fast environment light estimation from the RGBD appearance of individual objects and their local image areas. With the estimated lighting, virtual objects can be rendered in AR scenarios with shading that is consistent to the real scene.
  arXiv  Detail & Related papers  (2020-08-06T08:23:19Z)

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.