Jane Wu
@janehwu.bsky.social
Postdoc @ UC Berkeley. 3D Vision/Graphics/Robotics. Prev: CS PhD @ Stanford.
janehwu.github.io
janehwu.github.io
This project started as a cold email back in 2020, and from it came a wonderful new collaboration and immense personal growth. It's not everyday that my research requires writing CUDA kernels..
Thank you to Diego Thomas (who will also be at WACV) and Ron Fedkiw for guiding me every step of the way!
Thank you to Diego Thomas (who will also be at WACV) and Ron Fedkiw for guiding me every step of the way!
February 28, 2025 at 8:40 PM
This project started as a cold email back in 2020, and from it came a wonderful new collaboration and immense personal growth. It's not everyday that my research requires writing CUDA kernels..
Thank you to Diego Thomas (who will also be at WACV) and Ron Fedkiw for guiding me every step of the way!
Thank you to Diego Thomas (who will also be at WACV) and Ron Fedkiw for guiding me every step of the way!
Our method is able to reconstruct a unified human mesh from in-the-wild images, where high-frequency details like cloth wrinkles can be recovered even in the absence of any ground truth 3D data.
February 28, 2025 at 8:40 PM
Our method is able to reconstruct a unified human mesh from in-the-wild images, where high-frequency details like cloth wrinkles can be recovered even in the absence of any ground truth 3D data.
In this paper, we introduce a low-cost, optimization-based method for 3D human reconstruction guided by inferred 2D normal maps.
Aiming for end-to-end differentiability, we derive analytical gradients to backpropagate from predicted normal maps to network-inferred SDF values on a tetrahedral mesh.
Aiming for end-to-end differentiability, we derive analytical gradients to backpropagate from predicted normal maps to network-inferred SDF values on a tetrahedral mesh.
February 28, 2025 at 8:40 PM
In this paper, we introduce a low-cost, optimization-based method for 3D human reconstruction guided by inferred 2D normal maps.
Aiming for end-to-end differentiability, we derive analytical gradients to backpropagate from predicted normal maps to network-inferred SDF values on a tetrahedral mesh.
Aiming for end-to-end differentiability, we derive analytical gradients to backpropagate from predicted normal maps to network-inferred SDF values on a tetrahedral mesh.
It all started with a question that can be best characterized as “born out of resource scarcity”: can we reconstruct humans from consumer-grade cameras without using *any* 3D training data? 🫠
(Half a PhD later) Yes, we can! 😮💨
(Half a PhD later) Yes, we can! 😮💨
February 28, 2025 at 8:40 PM
It all started with a question that can be best characterized as “born out of resource scarcity”: can we reconstruct humans from consumer-grade cameras without using *any* 3D training data? 🫠
(Half a PhD later) Yes, we can! 😮💨
(Half a PhD later) Yes, we can! 😮💨
Our method is able to reconstruct a unified human mesh from in-the-wild images, where high-frequency details like cloth wrinkles can be recovered even in the absence of any ground truth 3D data.
February 28, 2025 at 8:35 PM
Our method is able to reconstruct a unified human mesh from in-the-wild images, where high-frequency details like cloth wrinkles can be recovered even in the absence of any ground truth 3D data.
In this paper, we introduce a low-cost, optimization-based method for 3D human reconstruction guided by inferred 2D normal maps.
Aiming for end-to-end differentiability, we derive analytical gradients to backpropagate from predicted normal maps to network-inferred SDF values on a tetrahedral mesh.
Aiming for end-to-end differentiability, we derive analytical gradients to backpropagate from predicted normal maps to network-inferred SDF values on a tetrahedral mesh.
February 28, 2025 at 8:35 PM
In this paper, we introduce a low-cost, optimization-based method for 3D human reconstruction guided by inferred 2D normal maps.
Aiming for end-to-end differentiability, we derive analytical gradients to backpropagate from predicted normal maps to network-inferred SDF values on a tetrahedral mesh.
Aiming for end-to-end differentiability, we derive analytical gradients to backpropagate from predicted normal maps to network-inferred SDF values on a tetrahedral mesh.
It all started with a question that can be best characterized as “born out of resource scarcity”: can we reconstruct humans from consumer-grade cameras without using *any* 3D training data? 🫠
(Half a PhD later) Yes, we can! 😮💨
(Half a PhD later) Yes, we can! 😮💨
February 28, 2025 at 8:35 PM
It all started with a question that can be best characterized as “born out of resource scarcity”: can we reconstruct humans from consumer-grade cameras without using *any* 3D training data? 🫠
(Half a PhD later) Yes, we can! 😮💨
(Half a PhD later) Yes, we can! 😮💨