arXiv Computer Vision
Do Image Editing Models Understand Lighting?
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 11
Shedding Light: A Benchmark for Evaluating Lighting Understanding in Generative Image Models
The paper introduces a benchmark called Shedding Light to evaluate how well generative image models understand and reproduce lighting. The benchmark tests models by asking them to inpaint a simple object, called a light probe, into real photographs and then compares the generated probe to the ground truth to assess lighting direction, colour, and radiance. The authors provide a scalable protocol and open-source code and data for systematic assessment of photometric accuracy in future models.
arXiv Computer Vision
Oct 15
LAMP: 3D Source-Aware Lighting Estimation at Multiple Points
arXiv:2610.19266v1 Announce Type: new Abstract: Existing illumination estimation methods primarily recover lighting distributions for rendering, but typically leave the contributions of individual ph...
Hugging Face Trending Papers
Jul 23
Engine-Native Editable 3D World Reconstruction with Objects and Lighting
Editable 3D scene creation requires object instances and lights that can be inspected, moved, and imported into standard engines, yet existing single-image methods largely stop at room-scale geometry, baked/global illumination, or text-driven generation. We introduce Lumera (Light-aware Unified Engine-native Reconstruction and Assembly), a benchmark and reference pipeline for engine-native, light-aware 3D scene parsing from a single image.
arXiv AI
Jul 7
The Power of Light: Improving Synthetic-to-Real Domain Adaptation through Physically-Based Indirect Illumination
arXiv:2606. 22574v2 Announce Type: replace-cross Abstract: While synthetic data generation resolves the manual labeling bottleneck in computer vision, minimizing the syn-to-real domain gap requires optimizing rendering variables.
arXiv AI
Sep 10
WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting
WildRelight is the first in-the-wild dataset designed to evaluate single-image relighting models, featuring high-resolution outdoor scenes captured under strictly aligned, temporally varying natural illuminations paired with high-dynamic-range environment maps. The benchmark demonstrates that state-of-the-art models trained on synthetic data suffer severe domain shifts when applied to real-world imagery. Leveraging the dataset’s temporal structure, the authors introduce a physics-guided inference framework combining Diffusion Posterior Sampling with Temporal Sampling-Aware Test-Time Adaptation, enabling synthetic models to self-supervise and align with real-world statistics on-the-fly.
arXiv Computer Vision
Sep 1
LightFuse: Relightable Interactive Gaussian Scene Reconstruction via Multi-Scan Fusion and 2D Gaussian Ray Tracing
arXiv:2608.29269v1 Announce Type: new Abstract: Relightable interactive scene reconstruction aims to build an editable 3D model from scans of different object arrangements and render new layouts unde...