GAINS: Gaussian-based Inverse Rendering from Sparse Multi-View Captures
This work addresses a domain-specific problem in computer vision for 3D reconstruction and rendering, offering incremental improvements for sparse-view settings.
The paper tackles the problem of material recovery from sparse multi-view captures, where existing methods degrade due to ambiguity between geometry, reflectance, and lighting, and introduces GAINS, a two-stage framework that improves material parameter accuracy and relighting quality compared to state-of-the-art methods.
Recent advances in Gaussian Splatting-based inverse rendering extend Gaussian primitives with shading parameters and physically grounded light transport, enabling high-quality material recovery from dense multi-view captures. However, these methods degrade sharply under sparse-view settings, where limited observations lead to severe ambiguity between geometry, reflectance, and lighting. We introduce GAINS (Gaussian-based Inverse rendering from Sparse multi-view captures), a two-stage inverse rendering framework that leverages learning-based priors to stabilize geometry and material estimation. GAINS first refines geometry using monocular depth/normal and diffusion priors, then employs segmentation, intrinsic image decomposition (IID), and diffusion priors to regularize material recovery. Extensive experiments on synthetic and real-world datasets show that GAINS significantly improves material parameter accuracy, relighting quality, and novel-view synthesis compared to state-of-the-art Gaussian-based inverse rendering methods, especially under sparse-view settings. Project page: https://patrickbail.github.io/gains/