no code implementations • 6 Apr 2023 • Akshay Krishnan, Amit Raj, Xianling Zhang, Alexandra Carlson, Nathan Tseng, Sandhya Sridhar, Nikita Jaipuria, James Hays
Specifically, we learn a scene representation that disentangles the static background and transient elements into a world-NeRF and class-specific object-NeRFs to allow compositional synthesis of multiple objects in the scene.
no code implementations • 2 Sep 2022 • Alexandra Carlson, Manikandasriram Srinivasan Ramanagopal, Nathan Tseng, Matthew Johnson-Roberson, Ram Vasudevan, Katherine A. Skinner
Recent advances in neural radiance fields (NeRFs) achieve state-of-the-art novel view synthesis and facilitate dense estimation of scene properties.
no code implementations • 23 Sep 2019 • Alexandra Carlson, Ram Vasudevan, Matthew Johnson-Roberson
There have been impressive advances in the realm of image to image translation in transferring previously unseen visual effects into a dataset, specifically in day to night translation.
no code implementations • 17 Sep 2018 • Alexandra Carlson, Katherine A. Skinner, Ram Vasudevan, Matthew Johnson-Roberson
This domain shift is especially exaggerated between synthetic and real datasets.
1 code implementation • 21 Mar 2018 • Alexandra Carlson, Katherine A. Skinner, Ram Vasudevan, Matthew Johnson-Roberson
Recent work has focused on generating synthetic imagery to increase the size and variability of training data for learning visual tasks in urban scenes.