paper-with-me

Papers

SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fields

2024-09-06 · Yuze Wang, Junyi Wang, Chen Wang, Wantong Duan, Yongtang Bao, Yue Qi

This paper introduces a novel continual learning framework for synthesising novel views of multiple scenes, learning multiple 3D scenes incrementally, and updating the network parameters only with the training data of the upcoming new scene. We build on Neural Radiance Fields (NeRF), which uses multi-layer perceptron to model the density and radiance field of a scene as the implicit function. While NeRF and its extensions have shown a powerful capability of rendering photo-realistic novel views in a single 3D scene, managing these growing 3D NeRF assets efficiently is a new scientific problem. Very few works focus on the efficient representation or continuous learning capability of multiple scenes, which is crucial for the practical applications of NeRF. To achieve these goals, our key idea is to represent multiple scenes as the linear combination of a cross-scene weight matrix and a set of scene-specific weight matrices generated from a global parameter generator. Furthermore, we propose an uncertain surface knowledge distillation strategy to transfer the radiance field knowledge of previous scenes to the new model. Representing multiple 3D scenes with such weight matrices significantly reduces memory requirements. At the same time, the uncertain surface distillation strategy greatly overcomes the catastrophic forgetting problem and maintains the photo-realistic rendering quality of previous scenes. Experiments show that the proposed approach achieves state-of-the-art rendering quality of continual learning NeRF on NeRF-Synthetic, LLFF, and TanksAndTemples datasets while preserving extra low storage cost.

📄 PDF Abstract BibTeX arXiv:2409.04482

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningKnowledge DistillationNeRF

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Focus 설명 없음
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

A System for Comprehensive Assessment of RAG Frameworks

2025-04-10 · Mattia Rengo, Senad Beadini, Domenico Alfano, Roberto Abbruzzese

Retrieval Augmented Generation (RAG) has emerged as a standard paradigm for enhancing the factual accuracy and contextual relevance of Large Language Models (LLMs) by integrating retrieval mechanisms. However, existing e…

RAGRetrievalRetrieval-augmented Generation

Shared LoRA Subspaces for almost Strict Continual Learning

2026-02-05 · Prakhar Kaushik, Ankit Vaidya, Shravan Chaudhari, Rama Chellappa 외 arxiv

Adapting large pretrained models to new tasks efficiently and continually is crucial for real-world deployment but remains challenging due to catastrophic forgetting and the high cost of retraining. While parameter-effic…

Natural Language UnderstandingText-to-Image GenerationImage ClassificationContinual Learning

DOLFIN: Balancing Stability and Plasticity in Federated Continual Learning

2025-10-15 · Omayma Moussadek, Riccardo Salami, Simone Calderara arxiv

Federated continual learning (FCL) enables models to learn new tasks across multiple distributed clients, protecting privacy and without forgetting previously acquired knowledge. However, current methods face challenges …

Incremental LearningContinual Learning

SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption

2021-06-29 · ICLR 2022 4 · Dara Bahri, Heinrich Jiang, Yi Tay, Donald Metzler

Self-supervised contrastive representation learning has proved incredibly successful in the vision and natural language domains, enabling state-of-the-art performance with orders of magnitude less labeled data. However, …

Contrastive LearningRepresentation Learningtabular-classification

Memory-Free Continual Learning with Null Space Adaptation for Zero-Shot Vision-Language Models

2025-10-24 · Yujin Jo, Taesup Kim arxiv

Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalization, enabling deployment in a wide range of real-world tasks without additional task-specific training. However, …

Zero-shot GeneralizationContinual Learning