NeuVV: Neural Volumetric Videos with Immersive Rendering and Editing

TL;DR

NeuVV introduces a neural volumetric video technique enabling real-time, immersive, and editable photorealistic 3D content rendering and editing for virtual environments, addressing limitations of traditional 3D reconstruction methods.

Contribution

The paper presents NeuVV, a novel neural volumography method that encodes dynamic neural radiance fields into renderable primitives, enabling real-time immersive rendering and editing of volumetric videos.

Findings

Supports real-time, photorealistic volumetric video rendering.

Enables interactive editing like repositioning and recoloring in virtual space.

Reduces training time and memory with VOctree integration.

Abstract

Some of the most exciting experiences that Metaverse promises to offer, for instance, live interactions with virtual characters in virtual environments, require real-time photo-realistic rendering. 3D reconstruction approaches to rendering, active or passive, still require extensive cleanup work to fix the meshes or point clouds. In this paper, we present a neural volumography technique called neural volumetric video or NeuVV to support immersive, interactive, and spatial-temporal rendering of volumetric video contents with photo-realism and in real-time. The core of NeuVV is to efficiently encode a dynamic neural radiance field (NeRF) into renderable and editable primitives. We introduce two types of factorization schemes: a hyper-spherical harmonics (HH) decomposition for modeling smooth color variations over space and time and a learnable basis representation for modeling abrupt density and color changes caused by motion. NeuVV factorization can be integrated into a Video Octree (VOctree) analogous to PlenOctree to significantly accelerate training while reducing memory overhead. Real-time NeuVV rendering further enables a class of immersive content editing tools. Specifically, NeuVV treats each VOctree as a primitive and implements volume-based depth ordering and alpha blending to realize spatial-temporal compositions for content re-purposing. For example, we demonstrate positioning varied manifestations of the same performance at different 3D locations with different timing, adjusting color/texture of the performer's clothing, casting spotlight shadows and synthesizing distance falloff lighting, etc, all at an interactive speed. We further develop a hybrid neural-rasterization rendering framework to support consumer-level VR headsets so that the aforementioned volumetric video viewing and editing, for the first time, can be conducted immersively in virtual 3D space.