NTIRE 2022 challenge on learning the super-resolution space
This paper reviews the NTIRE 2022 challenge on learning the super-Resolution space. This
challenge aims to raise awareness that the super-resolution problem is ill-posed. Since …
challenge aims to raise awareness that the super-resolution problem is ill-posed. Since …
Towards implicit text-guided 3d shape generation
In this work, we explore the challenging task of generating 3D shapes from text. Beyond the
existing works, we propose a new approach for text-guided 3D shape generation, capable of …
existing works, we propose a new approach for text-guided 3D shape generation, capable of …
ReduNet: A white-box deep network from the principle of maximizing rate reduction
This work attempts to provide a plausible theoretical framework that aims to interpret modern
deep (convolutional) networks from the principles of data compression and discriminative …
deep (convolutional) networks from the principles of data compression and discriminative …
Learning diverse and discriminative representations via the principle of maximal coding rate reduction
To learn intrinsic low-dimensional structures from high-dimensional data that most
discriminate between classes, we propose the principle of {\em Maximal Coding Rate …
discriminate between classes, we propose the principle of {\em Maximal Coding Rate …
Papr: Proximity attention point rendering
Learning accurate and parsimonious point cloud representations of scene surfaces from
scratch remains a challenge in 3D representation learning. Existing point-based methods …
scratch remains a challenge in 3D representation learning. Existing point-based methods …
Scade: Nerfs from space carving with ambiguity-aware depth estimates
MA Uy, R Martin-Brualla… - Proceedings of the …, 2023 - openaccess.thecvf.com
Neural radiance fields (NeRFs) have enabled high fidelity 3D reconstruction from multiple
2D input views. However, a well-known drawback of NeRFs is the less-than-ideal …
2D input views. However, a well-known drawback of NeRFs is the less-than-ideal …
GAN-based synthetic data augmentation for infrared small target detection
JH Kim, Y Hwang - IEEE Transactions on Geoscience and …, 2022 - ieeexplore.ieee.org
Recently, convolutional neural networks (CNNs) have achieved state-of-the-art performance
in infrared small target detection. However, the limited number of public training data …
in infrared small target detection. However, the limited number of public training data …
Difffacto: Controllable part-based 3d point cloud generation with cross diffusion
While the community of 3D point cloud generation has witnessed a big growth in recent
years, there still lacks an effective way to enable intuitive user control in the generation …
years, there still lacks an effective way to enable intuitive user control in the generation …
[HTML][HTML] Ctrl: Closed-loop transcription to an ldr via minimaxing rate reduction
This work proposes a new computational framework for learning a structured generative
model for real-world datasets. In particular, we propose to learn a C losed-loop Tr …
model for real-world datasets. In particular, we propose to learn a C losed-loop Tr …
Multimodal shape completion via implicit maximum likelihood estimation
Shape completion is the problem of completing partial input shapes such as partial scans.
This problem finds important applications in computer vision and robotics due to issues such …
This problem finds important applications in computer vision and robotics due to issues such …