“Denoising Monte Carlo Renders with Diffusion Models” by Vavilala, Vasanth and Forsyth
Conference:
Type(s):
Title:
- Denoising Monte Carlo Renders with Diffusion Models
Session/Category Title: Rendering & Displays
Presenter(s)/Author(s):
Abstract:
We demonstrate that large-scale pretrained image models can solve a classic computer graphics problem: removing ray-tracing noise, and our method is competitive with state-of-the-art works.
References:
[1]
Attila T. ?fra. 2024. Intel? Open Image Denoise. https://www.openimagedenoise.org.
[2]
Stability AI. 2024. DeepFloydIF. https://github.com/deep-floyd/IF.
Google Scholar
[3]
Mustafa I??k, Krishna Mullia, Matthew Fisher, Jonathan Eisenmann, and Micha?l Gharbi. 2021. Interactive Monte Carlo denoising using affinity of neural features. ACM Trans. Graph. 40, 4, Article 37 (jul 2021). https://doi.org/10.1145/3450626.3459793
[4]
Axel Sauer, Frederic Boesel, Tim Dockhorn, Andreas Blattmann, Patrick Esser, and Robin Rombach. 2024. Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation. arXiv preprint arXiv:2403.12015 (2024).
[5]
Jiaqi Yu, Yongwei Nie, Chengjiang Long, Wenju Xu, Qing Zhang, and Guiqing Li. 2021. Monte Carlo denoising via auxiliary feature guided self-attention. ACM Trans. Graph. 40, 6, Article 273 (dec 2021), 13 pages. https://doi.org/10.1145/3478513.3480565
