Advances in Radiance Field for Dynamic Scene: From Neural Field to Gaussian Field

TL;DR

This survey reviews over 200 papers on dynamic scene representation using radiance fields, highlighting recent advances from neural to Gaussian methods, and discusses challenges and future directions in the field.

Contribution

It provides a comprehensive systematic analysis and categorization of recent methods in dynamic scene radiance field research, unifying diverse approaches under a common framework.

Findings

Enhanced motion representation and scene reconstruction quality.

Identification of key challenges and promising research directions.

Systematic categorization of over 200 recent papers.

Abstract

Dynamic scene representation and reconstruction have undergone transformative advances in recent years, catalyzed by breakthroughs in neural radiance fields and 3D Gaussian splatting techniques. While initially developed for static environments, these methodologies have rapidly evolved to address the complexities inherent in 4D dynamic scenes through an expansive body of research. Coupled with innovations in differentiable volumetric rendering, these approaches have significantly enhanced the quality of motion representation and dynamic scene reconstruction, thereby garnering substantial attention from the computer vision and graphics communities. This survey presents a systematic analysis of over 200 papers focused on dynamic scene representation using radiance field, spanning the spectrum from implicit neural representations to explicit Gaussian primitives. We categorize and evaluate these works through multiple critical lenses: motion representation paradigms, reconstruction techniques for varied scene dynamics, auxiliary information integration strategies, and regularization approaches that ensure temporal consistency and physical plausibility. We organize diverse methodological approaches under a unified representational framework, concluding with a critical examination of persistent challenges and promising research directions. By providing this comprehensive overview, we aim to establish a definitive reference for researchers entering this rapidly evolving field while offering experienced practitioners a systematic understanding of both conceptual principles and practical frontiers in dynamic scene reconstruction.