This work synergizes both static and flash lighting from casual indoor capture, with the flash on or off, each from independent viewpoints, and renders static lighting with deferred shading such that it can also supervise material decomposition.
Abstract
Recovering geometry, materials, and lighting from photographs is highly ambiguous when only static illumination is available. Active-lighting setups reduce the ambiguity but require dark rooms or specialized hardware. Instead, we synergize both static and flash lighting from casual indoor capture, with the flash on or off, each from independent viewpoints. The flash residual constrains albedo and the BRDF, while static lighting captures grazing-angle specular highlights that flash misses. With a 2DGS reconstruction framing, our key contribution is a GS-anchored diffuse field: a hash-encoded MLP is queried at the rasterized 2DGS depth. As it depends only on world position, it is view consistent in 3D and allows the flash residual to drive material decomposition instead of being absorbed by alpha-blending drift across views. At the same time, we render static lighting with deferred shading such that it can also supervise material decomposition. On five synthetic and three real indoor scenes, our method outperforms six recent baselines on diffuse color, albedo and roughness material parameters, and in relighting where PSNR improves by 4.17 dB over the next-best baseline.
A surface photographed under even light presents nearly the same appearance from every angle; the same surface under uneven light does not. Exposure changes between views, illumination varies within a single image, and locally strong light sources leave one region bright and its neighbor in shadow. Multi-view reconstru...
Tong Wu, Jacob Edwards, Ziteng Cui et al.· 0 citations
Inverse rendering decomposes a scene into geometry, materials, and lighting to enable physically consistent view synthesis and relighting. Inverse rendering approaches built upon Gaussian Splatting benefit from its efficient reconstruction pipeline, yet they struggle in the presence of strong shadows. Shadows are often...
Kotoka Matsunaga, Xue-Ning Tian, Hideo Saito et al.· IEEE Open Journal of Signal...· 0 citations
Reference-based 3D scene stylization transfers the appearance of a reference image onto a reconstructed 3D scene while preserving scene geometry. Recent methods perform this transfer by optimizing the appearance representation of neural scene models including Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DG...
Wan-Rong Hong, Liu Jiang, Mukesh Prasad et al.· 0 citations
Standard 3D Gaussian Splatting (3DGS) learns geometry and appearance jointly from RGB supervision, making it difficult to isolate how luminance and chroma contribute to the learned representation. We study this by training models under different channel supervision, freezing their non-appearance parameters (position, s...
Binocular rendering requires two nearby views of the same scene and therefore repeats substantial visibility and shading work. We present a 2D Gaussian Splatting (2DGS) pipeline that fully renders a dominant-eye RGB image and an alpha-weighted depth proxy, reprojects that image to the affiliated eye, and repairs uncove...
Replacing a visible advertisement in a broadcast frame is geometrically straightforward but photometrically delicate. A pasted graphic can have the correct perspective and still appear detached when its brightness, shading, or shadow disagrees with the surface beneath it. This paper presents Ad-Relight, an inference-on...
Rameshwar Mishra, Bishshoy Das, A. V. Subramanyam et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.