A hybrid pipeline that renders bracelets with 3D Gaussian Splatting and then refines each frame with a diffusion model yields realistic, temporally consistent bracelet insertion into dynamic wrist videos.
SIDNet: Learning Shading-aware Illumination Descriptor for Image Harmonization
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Image harmonization aims at adjusting the appearance of the foreground to make it more compatible with the background. Without exploring background illumination and its effects on the foreground elements, existing works are incapable of generating a realistic foreground shading. In this paper, we decompose the image harmonization task into two sub-problems: 1) illumination estimation of the background image and 2) re-rendering of foreground objects under background illumination. Before solving these two sub-problems, we first learn a shading-aware illumination descriptor via a well-designed neural rendering framework, of which the key is a shading bases module that generates multiple shading bases from the foreground image. Then we design a background illumination estimation module to extract the illumination descriptor from the background. Finally, the Shading-aware Illumination Descriptor is used in conjunction with the neural rendering framework (SIDNet) to produce the harmonized foreground image containing a novel harmonized shading. Moreover, we construct a photo-realistic synthetic image harmonization dataset that contains numerous shading variations with image-based lighting. Extensive experiments on both synthetic and real data demonstrate the superiority of the proposed method, especially in dealing with foreground shadings.
citation-role summary
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videos
A hybrid pipeline that renders bracelets with 3D Gaussian Splatting and then refines each frame with a diffusion model yields realistic, temporally consistent bracelet insertion into dynamic wrist videos.