Dynamic Scene Reconstruction: Recent Advance in Real-time Rendering and Streaming
It provides a comprehensive overview for researchers in computer vision and graphics, but is incremental as it summarizes existing work.
This survey reviews over 170 papers on dynamic scene reconstruction from 2D images, focusing on Neural Radiance Fields and 3D Gaussian Splatting methods, and compares their performance on benchmarks.
Representing and rendering dynamic scenes from 2D images is a fundamental yet challenging problem in computer vision and graphics. This survey provides a comprehensive review of the evolution and advancements in dynamic scene representation and rendering, with a particular emphasis on recent progress in Neural Radiance Fields based and 3D Gaussian Splatting based reconstruction methods. We systematically summarize existing approaches, categorize them according to their core principles, compile relevant datasets, compare the performance of various methods on these benchmarks, and explore the challenges and future research directions in this rapidly evolving field. In total, we review over 170 relevant papers, offering a broad perspective on the state of the art in this domain.