paper-with-me

Papers

Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding

2023-03-22 · ICCV 2023 1 · Ziyang Yuan, Yiming Zhu, Yu Li, Hongyu Liu, Chun Yuan

3D GAN inversion aims to achieve high reconstruction fidelity and reasonable 3D geometry simultaneously from a single image input. However, existing 3D GAN inversion methods rely on time-consuming optimization for each individual case. In this work, we introduce a novel encoder-based inversion framework based on EG3D, one of the most widely-used 3D GAN models. We leverage the inherent properties of EG3D's latent space to design a discriminator and a background depth regularization. This enables us to train a geometry-aware encoder capable of converting the input image into corresponding latent code. Additionally, we explore the feature space of EG3D and develop an adaptive refinement stage that improves the representation ability of features in EG3D to enhance the recovery of fine-grained textural details. Finally, we propose an occlusion-aware fusion operation to prevent distortion in unobserved regions. Our method achieves impressive results comparable to optimization-based methods while operating up to 500 times faster. Our framework is well-suited for applications such as semantic editing.

📄 PDF Abstract BibTeX arXiv:2303.12326

Code (0)

등록된 구현이 없습니다.

Tasks

3D geometry

Similar Papers 제목 키워드 기반

The Illusion of Control: Why Bare Classifier Inversion Silently Fails in Concept-Bottleneck Text Generation

2026-08-24 · Qi Bing, Xiaowei Shao arxiv

Concept-bottleneck controllable generation routes multi-attribute control through a low-dimensional concept code that, at deployment, must be synthesised from a target attribute configuration. We study this problem in co…

Text Generation

Model Inversion Attacks against Graph Neural Networks

2022-09-16 · Zaixi Zhang, Qi Liu, Zhenya Huang, Hao Wang 외

Many data mining tasks rely on graphs to model relational structures among individuals (nodes). Since relational data are often sensitive, there is an urgent need to evaluate the privacy risks in graph data. One famous p…

modelReinforcement Learning (RL)

Differentially Private Data Generative Models

2018-12-06 · Qingrong Chen, Chong Xiang, Minhui Xue, Bo Li 외

Deep neural networks (DNNs) have recently been widely adopted in various applications, and such success is largely due to a combination of algorithmic breakthroughs, computation resource improvements, and access to a lar…

BIG-bench Machine LearningFederated LearningInference AttackMembership Inference Attack

Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks

2024-08-21 · Yiyi Chen, Russa Biswas, Heather Lent, Johannes Bjerva

Large Language Models (LLMs) are susceptible to malicious influence by cyber attackers through intrusions such as adversarial, backdoor, and embedding inversion attacks. In response, the burgeoning field of LLM Security …

All

ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generation

2025-02-16 · Yiyi Chen, Qiongkai Xu, Johannes Bjerva

With the growing popularity of Large Language Models (LLMs) and vector databases, private textual data is increasingly processed and stored as numerical embeddings. However, recent studies have proven that such embedding…