Enhancing Temporal Smoothing in Dynamic Neural Radiance Fields

Loading...
Thumbnail Image
Date
2025
Authors
Вербицька, Марія
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In this work, we conduct an end-to-end training and fine-tuning process for the Neural Radiance Field (NeRF) model [1] and introduce 4 experimental cases with filtering techniques [2] designed to strengthen the rendering performance. We evaluate our modifications on synthetic image data of the articulated objects. For this project, we chose the architecture of the Knowledge NeRF model [3]. It includes an original PyTorch NeRF implementation [4] alongside a projection module for dynamic scenes extension. Incorporating the rendering step adjustments allows for better results without requiring complete model re-training. Our study covers the theoretical basis of the 3D scene reconstruction problem [5] alongside the NeRF architecture, such as radiance field, volume rendering, the concept of coarse and fine networks etc. [1], provides a trained and fine-tuned model for one object of a specified motion type, and suggests four methods to handle postprocessing in Knowledge NeRF better.
Description
Keywords
neural radiance fields, view synthesis, dynamic scenes, blender dataset, filtering, 3D scene reconstruction, bachelor`s thesis
Citation