Search papers, labs, and topics across Lattice.
This paper introduces FreeLit, a novel framework for indoor scene relighting that eliminates the need for paired illumination datasets by leveraging physics-guided diffusion. By constructing a structured lightmap from intrinsic scene properties and utilizing a relighting-guided intrinsic stabilization strategy, FreeLit achieves robust and controllable relighting even in challenging low-light conditions. Experimental results show that FreeLit not only maintains physical consistency but also enhances user control over light-source characteristics without the limitations of traditional paired methods.
FreeLit achieves stable and controllable indoor relighting without the costly and restrictive need for paired illumination datasets.
Image-based indoor scene relighting remains challenging due to the complex interplay between cluttered geometry and local illumination, requiring precise modeling of light position, color, and intensity. Existing data-driven methods implicitly learn this relationship via paired multi-illumination datasets. Nevertheless, this data is costly and fails to scale, which is essential for accurate light-source-level control. Conversely, inverse-rendering methods reduce the data dependency by incorporating physical priors; however, they lack the robustness of intrinsic estimation in challenging conditions. In this paper, we present FreeLit, a paired-free framework for controllable indoor relighting that explicitly manipulates light-source location, color, and intensity. Instead of relying on paired supervision, we construct a physics-guided illumination prior from intrinsic scene properties, generating a structured lightmap along with a pseudo-relit image to guide diffusion-based synthesis. To address instability in intrinsic estimation, especially in low-light scenes, we introduce a relighting-guided intrinsic stabilization strategy that enforces illumination-invariant reflectance through structure-aware distillation and consistency constraints. Furthermore, we propose controllability-oriented evaluation metrics to quantify alignment with user-specified illumination color and intensity. Experimental results demonstrate that FreeLit achieves stable, physically consistent, and controllable relighting, with improved robustness in low-light indoor scenes, without requiring paired supervision.
