{"ID":2883915,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.08384","arxiv_id":"2508.08384","title":"Spatiotemporally Consistent Indoor Lighting Estimation with Diffusion Priors","abstract":"Indoor lighting estimation from a single image or video remains a challenge due to its highly ill-posed nature, especially when the lighting condition of the scene varies spatially and temporally. We propose a method that estimates from an input video a continuous light field describing the spatiotemporally varying lighting of the scene. We leverage 2D diffusion priors for optimizing such light field represented as a MLP. To enable zero-shot generalization to in-the-wild scenes, we fine-tune a pre-trained image diffusion model to predict lighting at multiple locations by jointly inpainting multiple chrome balls as light probes. We evaluate our method on indoor lighting estimation from a single image or video and show superior performance over compared baselines. Most importantly, we highlight results on spatiotemporally consistent lighting estimation from in-the-wild videos, which is rarely demonstrated in previous works.","short_abstract":"Indoor lighting estimation from a single image or video remains a challenge due to its highly ill-posed nature, especially when the lighting condition of the scene varies spatially and temporally. We propose a method that estimates from an input video a continuous light field describing the spatiotemporally varying lig...","url_abs":"https://arxiv.org/abs/2508.08384","url_pdf":"https://arxiv.org/pdf/2508.08384v1","authors":"[\"Mutian Tong\",\"Rundi Wu\",\"Changxi Zheng\"]","published":"2025-08-11T18:11:42Z","proceeding":"cs.GR","tasks":"[\"cs.GR\",\"cs.AI\",\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}