Semantic Interpolation in Implicit Models
In implicit models, one often interpolates between sampled points in latent space. As we show in this paper, care needs to be taken to match-up the distributional assumptions on code vectors with the geometry of the interpolating paths. Otherwise, typical assumptions about the quality and semantics of in-between points may not be justified. Based on our analysis we propose to modify the prior code distribution to put significantly more probability mass closer to the origin. As a result, linear interpolation paths are not only shortest paths, but they are also guaranteed to pass through high-density regions, irrespective of the dimensionality of the latent space. Experiments on standard benchmark image datasets demonstrate clear visual improvements in the quality of the generated samples and exhibit more meaningful interpolation paths.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Semantic Implicit Neural Scene Representations With Semi-Supervised Training
The recent success of implicit neural scene representations has presented a viable new method for how we capture and store 3D scenes. Unlike conventional 3D representations, such as point clouds, which explicitly store s…
3D geometry3D Semantic SegmentationRepresentation LearningSegmentation+1Deep Feature Interpolation for Image Content Changes
We propose Deep Feature Interpolation (DFI), a new data-driven baseline for automatic high-resolution image transformation. As the name suggests, it relies only on simple linear interpolation of deep convolutional featur…
DreamMover: Leveraging the Prior of Diffusion Models for Image Interpolation with Large Motion
We study the problem of generating intermediate images from image pairs with large motion while maintaining semantic consistency. Due to the large motion, the intermediate semantic information may be absent in input imag…
Semantic correspondenceJoint Implicit Image Function for Guided Depth Super-Resolution
Guided depth super-resolution is a practical task where a low-resolution and noisy input depth map is restored to a high-resolution version, with the help of a high-resolution RGB guide image. Existing methods usually vi…
Graph AttentionSuper-ResolutionVIINTER: View Interpolation with Implicit Neural Representations of Images
We present VIINTER, a method for view interpolation by interpolating the implicit neural representation (INR) of the captured images. We leverage the learned code vector associated with each image and interpolate between…
Image ManipulationSuper-Resolution