Zobrazeno 1 - 10
of 24
pro vyhledávání: '"TZU-MAO LI"'
Autor:
Tzu-Mao Li, 李子懋
101
This thesis presents a method applying Stein''s Unbiased Risk Estimator (SURE) to adaptive sampling and reconstruction to reduce noise in Monte Carlo rendering. SURE is a general unbiased estimator for mean squared error (MSE) in statistics.
This thesis presents a method applying Stein''s Unbiased Risk Estimator (SURE) to adaptive sampling and reconstruction to reduce noise in Monte Carlo rendering. SURE is a general unbiased estimator for mean squared error (MSE) in statistics.
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/29450223589532565570
Publikováno v:
ACM Transactions on Graphics; Jun2024, Vol. 43 Issue 3, p1-21, 21p
Autor:
Karima Ma, Michael Gharbi, Andrew Adams, Shoaib Kamil, Tzu-Mao Li, Connelly Barnes, Jonathan Ragan-Kelley
Publikováno v:
ACM Transactions on Graphics. 41:1-18
We present a method to automatically synthesize efficient, high-quality demosaicking algorithms, across a range of computational budgets, given a loss function and training data. It performs a multi-objective, discrete-continuous optimization which s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0067490c0e632590d9779f95c1565ad0
https://doi.org/10.1145/3508461
https://doi.org/10.1145/3508461
Publikováno v:
ACM Transactions on Graphics. 40:1-10
We present an unbiased online Monte Carlo method for rendering with many lights. Our method adapts both the hierarchical light clustering and the sampling distribution to our collected samples. Designing such a method requires us to make clustering d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a6af8c8540e03a1752249ba55017549f
https://doi.org/10.1145/3478513.3480561
https://doi.org/10.1145/3478513.3480561
Publikováno v:
Proceedings of the ACM on Programming Languages. 5:1-28
We present a new algorithm to quickly generate high-performance GPU implementations of complex imaging and vision pipelines, directly from high-level Halide algorithm code. It is fully automatic, requiring no schedule templates or hand-optimized kern
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b181e28611d3f88902779db9d832f0bf
https://doi.org/10.1145/3485486
https://doi.org/10.1145/3485486
Autor:
Jesse Michel, Jonathan Ragan-Kelley, Kevin Mu, Tzu-Mao Li, Sai Praveen Bangaru, Gilbert Bernstein
Publikováno v:
ACM Transactions on Graphics. 40:1-18
Emerging research in computer graphics, inverse problems, and machine learning requires us to differentiate and optimize parametric discontinuities. These discontinuities appear in object boundaries, occlusion, contact, and sudden change over time. I
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dd5e1482458d5afeaffb8ba0a21ec886
https://doi.org/10.1145/3476576.3476671
https://doi.org/10.1145/3476576.3476671
Autor:
Sai Praveen Bangaru, Michael Gharbi, Fujun Luan, Tzu-Mao Li, Kalyan Sunkavalli, Milos Hasan, Sai Bi, Zexiang Xu, Gilbert Bernstein, Fredo Durand
We present a method to automatically compute correct gradients with respect to geometric scene parameters in neural SDF renderers. Recent physically-based differentiable rendering techniques for meshes have used edge-sampling to handle discontinuitie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::03ecc149c2b838d44e525710ac775896
http://arxiv.org/abs/2206.05344
http://arxiv.org/abs/2206.05344
Publikováno v:
ACM Transactions on Graphics. 39:1-18
Differentiable rendering computes derivatives of the light transport equation with respect to arbitrary 3D scene parameters, and enables various applications in inverse rendering and machine learning. We present an unbiased and efficient differentiab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::37a5ebccda0c77f16634e8f807756d06
https://doi.org/10.1145/3414685.3417833
https://doi.org/10.1145/3414685.3417833
Publikováno v:
ACM Transactions on Graphics. 39:1-15
We introduce a differentiable rasterizer that bridges the vector graphics and raster image domains, enabling powerful raster-based loss functions, optimization procedures, and machine learning techniques to edit and generate vector content. We observ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::782ce62f19611a34be7601720627d5ab
https://doi.org/10.1145/3414685.3417871
https://doi.org/10.1145/3414685.3417871
We design new visual illusions by finding "adversarial examples" for principled models of human perception -- specifically, for probabilistic models, which treat vision as Bayesian inference. To perform this search efficiently, we design a differenti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ee9ce0123c28c35d282181885d581ec7
http://arxiv.org/abs/2204.12301
http://arxiv.org/abs/2204.12301