paper-with-me

Papers

Self-supervised Learning for Enhancing Geometrical Modeling in 3D-Aware Generative Adversarial Network

2023-12-19 · Jiarong Guo, Xiaogang Xu, Hengshuang Zhao

3D-aware Generative Adversarial Networks (3D-GANs) currently exhibit artifacts in their 3D geometrical modeling, such as mesh imperfections and holes. These shortcomings are primarily attributed to the limited availability of annotated 3D data, leading to a constrained "valid latent area" for satisfactory modeling. To address this, we present a Self-Supervised Learning (SSL) technique tailored as an auxiliary loss for any 3D-GAN, designed to improve its 3D geometrical modeling capabilities. Our approach pioneers an inversion technique for 3D-GANs, integrating an encoder that performs adaptive spatially-varying range operations. Utilizing this inversion, we introduce the Cyclic Generative Constraint (CGC), aiming to densify the valid latent space. The CGC operates via augmented local latent vectors that maintain the same geometric form, and it imposes constraints on the cycle path outputs, specifically the generator-encoder-generator sequence. This SSL methodology seamlessly integrates with the inherent GAN loss, ensuring the integrity of pre-existing 3D-GAN architectures without necessitating alterations. We validate our approach with comprehensive experiments across various datasets and architectures, underscoring its efficacy. Our project website: https://3dgan-ssl.github.io

📄 PDF Abstract BibTeX arXiv:2312.11856

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial NetworkSelf-Supervised Learningvalid

Similar Papers 제목 키워드 기반

Handling geometrical variability in nonlinear reduced order modeling through Continuous Geometry-Aware DL-ROMs

2024-11-08 · Simone Brivio, Stefania Fresca, Andrea Manzoni

Deep Learning-based Reduced Order Models (DL-ROMs) provide nowadays a well-established class of accurate surrogate models for complex physical systems described by parametrized PDEs, by nonlinearly compressing the soluti…

Inductive Bias

Enhancing self-supervised monocular depth estimation with traditional visual odometry

2019-08-08 · Lorenzo Andraghetti, Panteleimon Myriokefalitakis, Pier Luigi Dovesi, Belen Luque 외

Estimating depth from a single image represents an attractive alternative to more traditional approaches leveraging multiple cameras. In this field, deep learning yielded outstanding results at the cost of needing large …

Depth And Camera MotionDepth EstimationMonocular Depth EstimationVisual Odometry

GPA-VGGT:Adapting VGGT to Large Scale Localization by Self-Supervised Learning with Geometry and Physics Aware Loss

2026-01-23 · Yangfan Xu, Lilian Zhang, Xiaofeng He, Pengdong Wu 외 arxiv

Transformer-based general visual geometry frameworks have shown promising performance in camera pose estimation and 3D scene understanding. Recent advancements in Visual Geometry Grounded Transformer (VGGT) models have s…

Self-Supervised LearningCamera Pose EstimationScene Understanding3D Reconstruction

E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training

2025-12-11 · Qitao Zhao, Hao Tan, Qianqian Wang, Sai Bi 외 arxiv

Self-supervised pre-training has driven rapid progress in foundation models for language, 2D images, and video, yet remains largely unexplored for learning 3D-aware representations from multi-view images. In this paper, …

3D ReconstructionPose Estimation

GAPS: Geometry-Aware, Physics-Based, Self-Supervised Neural Garment Draping

2023-12-03 · Ruochen Chen, Liming Chen, Shaifali Parashar

Recent neural, physics-based modeling of garment deformations allows faster and visually aesthetic results as opposed to the existing methods. Material-specific parameters are used by the formulation to control the garme…