paper-with-me

홈 › Papers

Bootstrap-GS: Self-Supervised Augmentation for High-Fidelity Gaussian Splatting

2024-04-29 · YiFei Gao, Kerui Ren, Jie Ou, Lei Wang, Jiaji Wu, Jun Cheng

Recent advancements in 3D Gaussian Splatting (3D-GS) have established new benchmarks for rendering quality and efficiency in 3D reconstruction. However, 3D-GS faces critical limitations when generating novel views that significantly deviate from those encountered during training. Moreover, issues such as dilation and aliasing arise during zoom operations. These challenges stem from a fundamental issue: training sampling deficiency. In this paper, we introduce a bootstrapping framework to address this problem. Our approach synthesizes pseudo-ground truth from novel views that align with the limited training set and reintegrates these synthesized views into the training pipeline. Experimental results demonstrate that our bootstrapping technique not only reduces artifacts but also improves quantitative metrics. Furthermore, our technique is highly adaptable, allowing various Gaussian-based method to benefit from its integration.

📄 PDF Abstract BibTeX arXiv:2404.18669

Code (0)

등록된 구현이 없습니다.

Tasks

3D ReconstructionNeural Rendering

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentations

2025-06-25 · Lorenzo Bini, Stephane Marchand-Maillet

We present LaplaceGNN, a novel self-supervised graph learning framework that bypasses the need for negative sampling by leveraging spectral bootstrapping techniques. Our method integrates Laplacian-based signals into the…

Graph Learning

Bootstrapped Representation Learning on Graphs

2021-03-08 · ICLR Workshop GTRL 2021 5 · Shantanu Thakoor, Corentin Tallec, Mohammad Gheshlaghi Azar, Remi Munos 외

Current state-of-the-art self-supervised learning methods for graph neural networks are based on contrastive learning. As such, they heavily depend on the construction of augmentations and negative examples. Increasing t…

Contrastive LearningLinear evaluationRepresentation LearningSelf-Supervised Learning

Bootstrap Your Own Variance

2023-12-06 · Polina Turishcheva, Jason Ramapuram, Sinead Williamson, Dan Busbridge 외

Understanding model uncertainty is important for many applications. We propose Bootstrap Your Own Variance (BYOV), combining Bootstrap Your Own Latent (BYOL), a negative-free Self-Supervised Learning (SSL) algorithm, wit…

Self-Supervised Learning

Self-supervised Graph Representation Learning via Bootstrapping

2020-11-10 · Feihu Che, Guohua Yang, Dawei Zhang, JianHua Tao 외

Graph neural networks~(GNNs) apply deep learning techniques to graph-structured data and have achieved promising performance in graph representation learning. However, existing GNNs rely heavily on enough labels or well-…

Graph Representation LearningRepresentation Learning

Bootstrapped Self-Supervised Training with Monocular Video for Semantic Segmentation and Depth Estimation

2021-03-19 · Yihao Zhang, John J. Leonard

For a robot deployed in the world, it is desirable to have the ability of autonomous learning to improve its initial pre-set knowledge. We formalize this as a bootstrapped self-supervised learning problem where a system …

Depth EstimationSelf-Supervised LearningSemantic Segmentation