LumiMotion: Improving Gaussian Relighting with Scene Dynamics

LumiMotion: Improving Gaussian Relighting with Scene Dynamics

Table of Contents

Abstract

In 3D reconstruction, the problem of inverse rendering, namely recovering the illumination of the scene and the material properties, is fundamental. Existing Gaussian Splatting-based methods primarily target static scenes and often assume simplified or moderate lighting to avoid entan- gling shadows with surface appearance. This limits their ability to accurately separate lighting effects from mate- rial properties, particularly in real-world conditions. We address this limitation by leveraging dynamic elements– regions of the scene that undergo motion–as a supervisory signal for inverse rendering. Motion reveals the same sur- faces under varying lighting conditions, providing stronger cues for disentangling material and illumination. This the- sis is supported by our experimental results which show we improve LPIPS by 23% for albedo estimation and by 15% for scene relighting relative to next-best baseline. To this end, we introduce LumiMotion, the first Gaussian-based approach that leverages dynamics for inverse rendering and operates in arbitrary dynamic scenes. Our method learns a dynamic 2D Gaussian Splatting representation that em- ploys a set of novel constraints which encourage the dy- namic regions of the scene to deform, while keeping static regions stable. As we demonstrate, this separation is crucial for correct optimization of the albedo. Finally, we release a new synthetic benchmark comprising five scenes under four lighting conditions, each in both static and dynamic variants, for the first time enabling systematic evaluation of inverse rendering methods in dynamic environments and challenging lighting.

Paper (CVPR 2026): Click here to read
arXiv: https://arxiv.org/abs/2604.10994

Related Posts

NegGS: Negative Gaussian Splatting

NegGS: Negative Gaussian Splatting

Abstract One of the key strengths of 3D rendering lies in its ability to simulate intricate scenes with high fidelity. Among the recent advancements, Gaussian Splatting has gained prominence for its fast training and inference capabilities.

Read More
CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting

CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting

Abstract We present CLIPGaussian, a framework that performs universal, multimodal style transfer by operating directly on Gaussian primitives—the shared representation underlying modern 2D, 3D, and 4D Gaussian Splatting pipelines. Instead of relying on heavy generative models, CLIPGaussian uses CLIP-driven text and image cues to steer both the appearance and, when beneficial, the geometry of Gaussian elements. This makes stylization a geometric-aware process: colors shift in locally meaningful ways, textures reorganize to match the target style, and structural details adapt subtly without disrupting the underlying scene. Because the method works natively on Gaussian fields, the same mechanism seamlessly applies to single images, complex 3D objects, temporally coherent videos, and dynamic 4D reconstructions.

Read More

University–Hospital Collaboration Conference (Kraków, 3 December 2025)

University–Hospital Collaboration Conference (Kraków, 3 December 2025) On 3 December 2025, the Krakow Specialist Hospital of St. John Paul II hosted the conference “University–Hospital Collaboration – New Opportunities” at the Conference and Training Center (Pavilion A5) in Kraków.

Read More