Work

A Query-Efficient Stochastic Volume Rendering Framework for Time-Varying Implicit Neural Volumes

Year: 2026

Type: preprint

Abstract: Time-varying implicit neural representations (INRs) provide a compact representation of scientific volumes and, for modalities such as dynamic X-ray computed tomography (CT), are often the only practical way to represent the data. However, interactive volume rendering of INRs is challenging, as cheap memory lookups are replaced by expensive neural inferences, hindering the performance. Therefore, conventional volume rendering methods such as ray marching with dense sampling are often impractical. While resampling, caching, and retraining can mitigate this cost, they compromise convenience and accuracy and become impractical for time-varying data. We tackle these challenges using a query-efficient stochastic volume rendering framework based on delta tracking. Our system employs a four-stage pipeline that exploits heterogeneous parallelism, using ray tracing cores for traversal and tensor cores for batched neural evaluation. Furthermore, we present strategies to reduce INR queries via ray budgeting and query pruning, thereby increasing per-frame performance. Using our renderer, many time-varying INRs can be rendered directly from their original representation. The system achieves ~30-40 FPS at 1024x1024 resolution on an RTX 4090 GPU and converges to high-fidelity images. Moreover, the system enables interactive temporal exploration of the continuous domain, with timestep updates taking approximately 1-2 ms.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2607.28047

Authors: Sahistan, Alper, Miao, Haichao, Li, Zhimin, Bremer, Peer-Timo, Levine, Joshua A, Pascucci, Valerio

Topic: Computer Graphics and Visualization Techniques

Subfield: Computer Graphics and Computer-Aided Design

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, U.S. Department of Energy, National Aeronautics and Space Administration, Office of International Science and Engineering, Laboratory Directed Research and Development, Lawrence Livermore National Laboratory

Awards: G1088636562, G1356433355, Global Centers Track 1: U.S.-Canada Center on Climate-Resilient Western Interconnected Grid, G2145270357, G2717806384, G3669113783, OAC: Piloting the National Science Data Fabric: A Platform Agnostic Testbed for Democratizing Data Delivery, G4744444288, G5630301777, NEUTRAL FIELD PROCESSING FOR VISUAL ANALYSIS, NEURAL FIELD PROCESSING FOR VISUAL ANALYSIS, G895790057, G991281326

OpenAlex ID: W7172013603

Cites:

Cited by:

Related to: