palliate
发表于 2025-3-30 08:51:51
,Neural Scene Decoration from a Single Photograph,d a 3D model of the space, decorate, and then perform rendering. Although the task is important, it is tedious and requires tremendous effort. In this paper, we introduce a new problem of domain-specific indoor scene image synthesis, namely neural scene decoration. Given a photograph of an empty ind
拱形面包
发表于 2025-3-30 16:03:34
http://reply.papertrans.cn/24/2343/234242/234242_52.png
Projection
发表于 2025-3-30 16:32:16
http://reply.papertrans.cn/24/2343/234242/234242_53.png
Bravura
发表于 2025-3-30 23:17:20
,ChunkyGAN: Real Image Inversion via Segments,al latent representation of the input image, our approach subdivides the input image into a set of smaller components (chunks) specified either manually or automatically using a pre-trained segmentation network. For each chunk, the latent code of a generative network is estimated locally with greate
patriot
发表于 2025-3-31 04:43:14
GAN Cocktail: Mixing GANs Without Dataset Access,ed for model merging: combining two or more pretrained generative models into a single unified one. In this work we tackle the problem of model merging, given two constraints that often come up in the real world: (1) no access to the original training data, and (2) without increasing the network siz
本土
发表于 2025-3-31 08:29:35
,Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering,mera views. Though existing NeRF-based methods can synthesize rather realistic details for human body, they tend to produce poor results when the input has self-occlusion, especially for unseen humans under sparse views. Moreover, these methods often require a large number of sampling points for ren
oxidize
发表于 2025-3-31 11:44:58
Controllable Shadow Generation Using Pixel Height Maps,ot always available. Deep learning-based shadow synthesis methods learn a mapping from the light information to an object’s shadow without explicitly modeling the shadow geometry. Still, they lack control and are prone to visual artifacts. We introduce “Pixel Height", a novel geometry representation
无聊的人
发表于 2025-3-31 15:28:53
http://reply.papertrans.cn/24/2343/234242/234242_58.png
Orthodontics
发表于 2025-3-31 19:38:39
Subspace Diffusion Generative Models,sary to run this entire process at high dimensionality and incur all the inconveniences thereof. Instead, we restrict the diffusion via projections onto . as the data distribution evolves toward noise. When applied to state-of-the-art models, our framework simultaneously . sample quality—reaching an
贸易
发表于 2025-3-31 21:56:23
,DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training, mode collapse. Built upon the Vanilla GAN’s two-player game between the discriminator . and the generator ., we introduce a peer discriminator . to the min-max game. Similar to previous work using two discriminators, the first role of both ., . is to distinguish between generated samples and real o