Zobrazeno 1 - 10
of 2 049
pro vyhledávání: '"Chan, Matthew"'
Autor:
Shah, Sachin, Chan, Matthew Albert, Cai, Haoming, Chen, Jingxi, Kulshrestha, Sakshum, Singh, Chahat Deep, Aloimonos, Yiannis, Metzler, Christopher
Point-spread-function (PSF) engineering is a well-established computational imaging technique that uses phase masks and other optical elements to embed extra information (e.g., depth) into the images captured by conventional CMOS image sensors. To da
Externí odkaz:
http://arxiv.org/abs/2406.09409
Autor:
Wang, Shengze, Li, Xueting, Liu, Chao, Chan, Matthew, Stengel, Michael, Spjut, Josef, Fuchs, Henry, De Mello, Shalini, Nagano, Koki
Recent breakthroughs in single-image 3D portrait reconstruction have enabled telepresence systems to stream 3D portrait videos from a single camera in real-time, potentially democratizing telepresence. However, per-frame 3D reconstruction exhibits te
Externí odkaz:
http://arxiv.org/abs/2405.00794
Estimating and disentangling epistemic uncertainty, uncertainty that is reducible with more training data, and aleatoric uncertainty, uncertainty that is inherent to the task at hand, is critically important when applying machine learning to high-sta
Externí odkaz:
http://arxiv.org/abs/2402.03478
Autor:
Trevithick, Alex, Chan, Matthew, Takikawa, Towaki, Iqbal, Umar, De Mello, Shalini, Chandraker, Manmohan, Ramamoorthi, Ravi, Nagano, Koki
3D-aware Generative Adversarial Networks (GANs) have shown remarkable progress in learning to generate multi-view-consistent images and 3D geometries of scenes from collections of 2D images via neural volume rendering. Yet, the significant memory and
Externí odkaz:
http://arxiv.org/abs/2401.02411
High dynamic range (HDR) images are important for a range of tasks, from navigation to consumer photography. Accordingly, a host of specialized HDR sensors have been developed, the most successful of which are based on capturing variable per-pixel ex
Externí odkaz:
http://arxiv.org/abs/2308.08094
Autor:
Han, Yi, Chan, Matthew, Wengrowski, Eric, Li, Zhuohuan, Tippenhauer, Nils Ole, Srivastava, Mani, Zonouz, Saman, Garcia, Luis
Camera-based autonomous systems that emulate human perception are increasingly being integrated into safety-critical platforms. Consequently, an established body of literature has emerged that explores adversarial attacks targeting the underlying mac
Externí odkaz:
http://arxiv.org/abs/2307.13131
Autor:
Chan, Matthew Yunho
Increased proliferation of nanotechnology has led to concerns regarding its implication to the water environment. Gold nanoparticles (AuNP) were used as a model nanomaterial to investigate the fate and dynamics of nanoparticles in the complex water e
Externí odkaz:
http://hdl.handle.net/10919/85437
Autor:
Trevithick, Alex, Chan, Matthew, Stengel, Michael, Chan, Eric R., Liu, Chao, Yu, Zhiding, Khamis, Sameh, Chandraker, Manmohan, Ramamoorthi, Ravi, Nagano, Koki
We present a one-shot method to infer and render a photorealistic 3D representation from a single unposed image (e.g., face portrait) in real-time. Given a single RGB input, our image encoder directly predicts a canonical triplane representation of a
Externí odkaz:
http://arxiv.org/abs/2305.02310
Autor:
Chan, Eric R., Nagano, Koki, Chan, Matthew A., Bergman, Alexander W., Park, Jeong Joon, Levy, Axel, Aittala, Miika, De Mello, Shalini, Karras, Tero, Wetzstein, Gordon
We present a diffusion-based model for 3D-aware generative novel view synthesis from as few as a single input image. Our model samples from the distribution of possible renderings consistent with the input and, even in the presence of ambiguity, is c
Externí odkaz:
http://arxiv.org/abs/2304.02602
Many imaging inverse problems$\unicode{x2014}$such as image-dependent in-painting and dehazing$\unicode{x2014}$are challenging because their forward models are unknown or depend on unknown latent parameters. While one can solve such problems by train
Externí odkaz:
http://arxiv.org/abs/2303.09642