Adaptive Time-step Training for Enhancing Spike-Based Neural Radiance Fields
By: Ranxi Lin , Canming Yao , Jiayi Li and more
Potential Business Impact:
Makes 3D pictures use less power and time.
Neural Radiance Fields (NeRF)-based models have achieved remarkable success in 3D reconstruction and rendering tasks. However, during both training and inference, these models rely heavily on dense point sampling along rays from multiple viewpoints, resulting in a surge in floating-point operations and severely limiting their use in resource-constrained scenarios like edge computing. Spiking Neural Networks (SNNs), which communicate via binary spikes over discrete time steps, offer a promising alternative due to their energy-efficient nature. Given the inherent variability in scene scale and texture complexity in neural rendering and the prevailing practice of training separate models per scene, we propose a spike-based NeRF framework with a dynamic time step training strategy, termed Pretrain-Adaptive Time-step Adjustment (PATA). This approach automatically explores the trade-off between rendering quality and time step length during training. Consequently, it enables scene-adaptive inference with variable time steps and reduces the additional consumption of computational resources in the inference process. Anchoring to the established Instant-NGP architecture, we evaluate our method across diverse datasets. The experimental results show that PATA can preserve rendering fidelity while reducing inference time steps by 64\% and running power by 61.55\%.
Similar Papers
Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness
Machine Learning (CS)
Makes computer brains work better on different speeds.
TimeNeRF: Building Generalizable Neural Radiance Fields across Time from Few-Shot Input Views
CV and Pattern Recognition
Makes videos show any time of day.
Ultra-Low-Latency Spiking Neural Networks with Temporal-Dependent Integrate-and-Fire Neuron Model for Objects Detection
CV and Pattern Recognition
Makes computers see objects faster and better.