1. [Publications](/publications)
2. Interactive Path Tracing and Reconstruction of Sparse Volumes
 
 # Interactive Path Tracing and Reconstruction of Sparse Volumes

  ![](/sites/default/files/styles/wide/public/publications/teaser.jpg?itok=tC-FeZBD)

 We combine state-of-the-art techniques into a system for high-quality, interactive rendering of participating media. We leverage *unbiased* volume path tracing with multiple scattering, temporally stable neural denoising and NanoVDB, a fast, sparse voxel tree data structure for the GPU, to explore what performance and image quality can be obtained for rendering volumetric data. Additionally, we integrate neural adaptive sampling to significantly improve image quality at a fixed sample budget. Our system runs at interactive rates at 1920 x 1080 on a single GPU and produces high quality results for complex dynamic volumes.



 ## Authors



Nikolai Hofmann (NVIDIA)

[Jon Hasselgren](/person/jon-hasselgren)

[Petrik Clarberg](/person/petrik-clarberg)

[Jacob Munkberg](/person/jacob-munkberg)

 

 

 ## Publication Date



Friday, March 19, 2021

 

 ## Published in



[Proceedings of the ACM on Computer Graphics and Interactive Techniques](https://dl.acm.org/loi/pacmcgit)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Computer Graphics](/research-area/computer-graphics)

[Real-Time Rendering](/research-area/real-time-rendering)

 

 

 ## Uploaded Files



[Preprint](https://d1qx31qr3h6wln.cloudfront.net/publications/paper_v3.pdf "Open file in new window")7.01 MB

[Video](https://d1qx31qr3h6wln.cloudfront.net/publications/final_video_v2.mp4 "Open video in new window")250.34 MB

 

 

 ## Award



Best Paper Presentation, i3D 2021