FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices with A Simple Super-Resolution Pipeline
원문 초록
Super-resolution (SR) techniques have recently been proposed to upscale the outputs of neural radiance fields (NeRF) and generate high-quality images with enhanced inference speeds. However, existing NeRF+SR methods increase training overhead by using extra input features, loss functions, and/or expensive training procedures such as knowledge distillation. In this paper, we aim to leverage SR for efficiency gains without costly training or architectural changes. Specifically, we build a simple NeRF+SR pipeline that directly combines existing modules, and we propose a lightweight augmentation technique, random patch sampling, for training. Compared to existing NeRF+SR methods, our pipeline mitigates the SR computing overhead and can be trained up to 23x faster, making it feasible to run on consumer devices such as the Apple MacBook. Experiments show our pipeline can upscale NeRF outputs by 2-4x while maintaining high quality, increasing inference speeds by up to 18x on an NVIDIA V100 GPU and 12.8x on an M1 Pro chip. We conclude that SR can be a simple but effective technique for improving the efficiency of NeRF models for consumer devices.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
HNOSeg-XS: Extremely Small Hartley Neural Operator for Efficient and Resolution-Robust 3D Image Segmentation
Efficient and Generalizable Speaker Diarization via Structured Pruning of Self-Supervised Models
R3eVision: A Survey on Robust Rendering, Restoration, and Enhancement for 3D Low-Level Vision
Plug-and-Play Linear Attention for Pre-trained Image and Video Restoration Models
GaussianVAE: Adaptive Learning Dynamics of 3D Gaussians for High-Fidelity Super-Resolution
Boosting Lightweight Single Image Super-resolution via Joint-distillation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.