FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting
3D Gaussian splatting (3DGS) has enabled various applications in 3D scene representation and novel view synthesis due to its efficient rendering capabilities. However, 3DGS demands significant GPU memory, limiting its use on devices with restricted computational resources. Previous approaches have focused on pruning less important Gaussians, effectively compressing 3DGS but often requiring a fine-tuning stage and lacking adaptability for the specific memory needs of different devices. In this work, we present an elastic inference method for 3DGS. Given an input for the desired model size, our method selects and transforms a subset of Gaussians, achieving substantial rendering performance without additional fine-tuning. We introduce a tiny learnable module that controls Gaussian selection based on the input percentage, along with a transformation module that adjusts the selected Gaussians to complement the performance of the reduced model. Comprehensive experiments on ZipNeRF, MipNeRF and Tanks&Temples scenes demonstrate the effectiveness of our approach. Code will be publicly available.
Code (0)
등록된 구현이 없습니다.
Tasks
3DGSGPUNovel View SynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Graph-based Strategic Sensor Deployment Approach for k-coverage in WSN
This paper studies a graph-based sensor deployment approach in wireless sensor networks (WSNs). Specifically, in today's world, where sensors are everywhere, detecting various attributes like temperature and movement, th…
Write Once, Run Everywhere: The Axon DSL for Shape-Safe and Framework-Agnostic LLM Architectures
The entire ecosystem of open-source language models effectively relies on a single platform. What if this platform was forced to shut down tomorrow? Implementing and maintaining efficient model definitions and translatin…
Everywhere Learning: Artificial Intelligence with Pointwise Constraints
Everywhere learning is a new paradigm whereby Artificial Intelligence (AI) systems are trained to satisfy loss constraints with probability one over the data distribution. This is in contrast to the standard paradigm of …
FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment
The growing scale of deep neural networks, encompassing large language models (LLMs) and vision transformers (ViTs), has made training from scratch prohibitively expensive and deployment increasingly costly. These models…
Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks
Backdoor attacks have become a significant threat to the pre-training and deployment of deep neural networks (DNNs). Although numerous methods for detecting and mitigating backdoor attacks have been proposed, most rely o…