SampleMono: Multi-Frame Spatiotemporal Extrapolation of 1-spp Path-Traced Sequences via Transfer Learning

dc.contributor.authorDerin, Mehmet Oguzen_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorHan, Ping-Hsuanen_US
dc.contributor.editorLin, Shih-Syunen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorSchneider, Teseoen_US
dc.contributor.editorTsai, Hsin-Rueyen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.contributor.editorZhang, Eugeneen_US
dc.date.accessioned2025-10-07T06:05:17Z
dc.date.available2025-10-07T06:05:17Z
dc.date.issued2025
dc.description.abstractPath-traced sequences at one sample per pixel (1-spp) are attractive for interactive previews but remain severely noisy, particularly under caustics, indirect lighting, and volumetric media. We present SampleMono, a novel approach that performs multi-frame spatiotemporal extrapolation of low-resolution and low-sample Monte Carlo sequences without requiring auxiliary buffers or scene-specific information. We transfer and prune a pre-trained video generation backbone and fine-tune it on SampleMono GYM, a synthetic Monte Carlo dataset, to generate four clean high-resolution frames from a longer window of noisy inputs, thereby decoupling render and presentation timelines. Our experiments demonstrate that by combining a frozen VAE encoder-decoder and training of a video generation model pruned to two transformer layers, our pipeline can both provide spatial upsampling and temporal extrapolation to a long sequence of 16 RGB frames of 50 milliseconds time delta between frames at 256×144 resolution with severe Monte Carlo noise, generating subsequent four RGB frames of 12.5 milliseconds time delta between frames at 1280×720 resolution with substantially reduced noise at varying quality while fitting VRAM budget of 5GB. We plan to publish the code for data GYM, model pruning, pipeline training, and rendering.en_US
dc.description.sectionheadersPosters and Demos
dc.description.seriesinformationPacific Graphics Conference Papers, Posters, and Demos
dc.identifier.doi10.2312/pg.20251307
dc.identifier.isbn978-3-03868-295-0
dc.identifier.pages2 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20251307
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20251307
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Transfer learning; Ray tracing; Tracking
dc.subjectComputing methodologies → Transfer learning
dc.subjectRay tracing
dc.subjectTracking
dc.titleSampleMono: Multi-Frame Spatiotemporal Extrapolation of 1-spp Path-Traced Sequences via Transfer Learningen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
pg20251307.pdf
Size:
1.68 MB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
poster1017_mm1.pdf
Size:
1.57 MB
Format:
Adobe Portable Document Format