Light diffuser plastic

We present a simple yet effective technique to estimate lighting in a single input image. Current techniques rely heavily on HDR panorama datasets to train neural networks to regress an input with limited field-of-view to a full environment map. However, these approaches often struggle with real-world, uncontrolled settings due to the limited diversity and size of their datasets. To address this problem, we leverage diffusion models trained on billions of standard images to render a chrome ball into the input image. Despite its simplicity, this task remains challenging: the diffusion models often insert incorrect or inconsistent objects and cannot readily generate images in HDR format. Our research uncovers a surprising relationship between the appearance of chrome balls and the initial diffusion noise map, which we utilize to consistently generate high-quality chrome balls. We further fine-tune an LDR diffusion model (Stable Diffusion XL) with LoRA, enabling it to perform exposure bracketing for HDR light estimation. Our method produces convincing light estimates across diverse settings and demonstrates superior generalization to in-the-wild scenarios.

The predicted light estimation will be located at /hdr and can be used for downstream tasks such as object insertion. We will also use it to compare with other methods.

Energy efficientlightingltd

Additionally, we provide a slightly modified version of the evaluation code at DiffusionLight-evaluation including the test input.

We use the evaluation code from StyleLight and Editable Indoor LightEstimation. You can use their code to measure our score.

Note that Conda is optional. However, if you choose not to use Conda, you must manually install CUDA-toolkit and OpenEXR.