NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Cameras
This enables immersive VR/AR experiences by improving detail and realism in human performance capture, though it is incremental over prior neural methods.
The paper tackles the problem of real-time 4D reconstruction and rendering of human activities from sparse multi-view RGB cameras, achieving high-quality geometry and photo-realistic texture in arbitrary novel views.
4D reconstruction and rendering of human activities is critical for immersive VR/AR experience.Recent advances still fail to recover fine geometry and texture results with the level of detail present in the input images from sparse multi-view RGB cameras. In this paper, we propose NeuralHumanFVV, a real-time neural human performance capture and rendering system to generate both high-quality geometry and photo-realistic texture of human activities in arbitrary novel views. We propose a neural geometry generation scheme with a hierarchical sampling strategy for real-time implicit geometry inference, as well as a novel neural blending scheme to generate high resolution (e.g., 1k) and photo-realistic texture results in the novel views. Furthermore, we adopt neural normal blending to enhance geometry details and formulate our neural geometry and texture rendering into a multi-task learning framework. Extensive experiments demonstrate the effectiveness of our approach to achieve high-quality geometry and photo-realistic free view-point reconstruction for challenging human performances.