paper-with-me

Papers

StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation

2021-12-21 · CVPR 2022 1 · Roy Or-El, Xuan Luo, Mengyi Shan, Eli Shechtman, Jeong Joon Park, Ira Kemelmacher-Shlizerman

We introduce a high resolution, 3D-consistent image and shape generation technique which we call StyleSDF. Our method is trained on single-view RGB data only, and stands on the shoulders of StyleGAN2 for image generation, while solving two main challenges in 3D-aware GANs: 1) high-resolution, view-consistent generation of the RGB images, and 2) detailed 3D shape. We achieve this by merging a SDF-based 3D representation with a style-based 2D generator. Our 3D implicit network renders low-resolution feature maps, from which the style-based network generates view-consistent, 1024x1024 images. Notably, our SDF-based 3D modeling defines detailed 3D surfaces, leading to consistent volume rendering. Our method shows higher quality results compared to state of the art in terms of visual and geometric quality.

📄 PDF Abstract BibTeX arXiv:2112.11427

Code (1)

royorel/StyleSDF 공식 구현 pytorch

Tasks

3D-Aware Image SynthesisFace GenerationImage GenerationVocal Bursts Intensity Prediction

Methods 이 논문이 사용한 방법론

Weight Demodulation 설명 없음
R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…
Path Length Regularization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…

Similar Papers 제목 키워드 기반

LatentSwap3D: Semantic Edits on 3D Image GANs

2022-12-02 · Enis Simsar, Alessio Tonioni, Evin Pınar Örnek, Federico Tombari

3D GANs have the ability to generate latent codes for entire 3D volumes rather than only 2D images. These models offer desirable features like high-quality geometry and multi-view consistency, but, unlike their 2D counte…

Feature Importance

What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

2024-01-04 · CVPR 2024 1 · Alex Trevithick, Matthew Chan, Towaki Takikawa, Umar Iqbal 외

3D-aware Generative Adversarial Networks (GANs) have shown remarkable progress in learning to generate multi-view-consistent images and 3D geometries of scenes from collections of 2D images via neural volume rendering. Y…

3D geometryNeural RenderingSuper-Resolution

HD-VGGT: High-Resolution Visual Geometry Transformer

2026-03-28 · Tianrun Chen, Yuanqi Hu, Yidong Han, Hanjie Xu 외 arxiv

High-resolution imagery is essential for accurate 3D reconstruction, as many geometric details only emerge at fine spatial scales. Recent feed-forward approaches, such as the Visual Geometry Grounded Transformer (VGGT), …

Feature Upsampling3D Reconstruction

Efficient Geometry-Controlled High-Resolution Satellite Image Synthesis

2026-05-06 · Vlad Vasilescu, Daniela Faur, Teodor Costachioiu arxiv

High-resolution satellite images are often scarce and costly, especially for remote areas or infrequent events. This shortage hampers the development and testing of machine learning models for land-cover classification, …

Change Detection

DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation

2026-03-04 · Tuan Duc Ngo, Jiahui Huang, Seoung Wug Oh, Kevin Blackburn-Matzen 외 arxiv

Estimating accurate, view-consistent geometry and camera poses from uncalibrated multi-view/video inputs remains challenging - especially at high spatial resolutions and over long sequences. We present DAGE, a dual-strea…