Temporal Gradient-domain Path Tracing

Marco Manzi1 Markus Kettunen2 Fredo Durand4 Matthias Zwicker1 Jaakko Lehtinen3
1University of Bern 2Aalto University 3Aalto University and Nvidia 4Massachusetts Institute of Technology

In ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia), 35(6), November 2016

In addition to standard path sampling, our method also estimates spatial, temporal and mixed finite differences for the frames of an animation. We then solve a 3D screened Poisson problem to reconstruct the animation whose frames best match the sampled data. b) Equal-time rolling shutter crops of the animation KITCHEN 2. The rows are extracted from sequential animation frames. Our method often reduces both spatial variance, seen as horizontal noise, and flickering, seen as vertical noise.


We present a novel approach to improve temporal coherence in Monte Carlo renderings of animation sequences. Unlike other approaches that exploit temporal coherence in a post-process, our technique does so already during sampling. Building on previous gradient-domain rendering techniques that sample finite differences over the image plane, we introduce temporal finite differences and formulate a corresponding 3D spatio-temporal screened Poisson reconstruction problem that is solved over windowed batches of several frames simultaneously. We further extend our approach to include second order, mixed spatio-temporal differences, an improved technique to compute temporal differences exploiting motion vectors, and adaptive sampling. Our algorithm can be built on a gradient-domain path tracer without large modifications. In particular, we do not require the ability to evaluate animation paths over multiple frames. We demonstrate that our approach effectively reduces temporal flickering in animation sequences, significantly improving the visual quality compared to both path tracing and gradient-domain rendering of individual frames.

Additional Information