Every paper, ordered by impact or potential impact. About CVPR 2022
| ID | Paper | Authors | Source | Date |
|---|---|---|---|---|
| 1 | High-Resolution Image Synthesis With Latent Diffusion Models IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: By introducing cross-attention layers into the model architecture, we turn diffusion models into powerful and flexible generators for general conditioning inputs such as text or bounding boxes and high-resolution synthesis becomes possible in a convolutional manner. | Robin Rombach; Andreas Blattmann; Dominik Lorenz et al. | cvpr | 2022-06-07 |
| 2 | Blended Diffusion for Text-Driven Editing of Natural Images IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we introduce the first solution for performing local (region-based) edits in generic natural images, based on a natural language description along with an ROI mask. | Omri Avrahami; Dani Lischinski; Ohad Fried; | cvpr | 2022-06-07 |
| 3 | Masked Autoencoders Are Scalable Vision Learners IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. | Kaiming He; Xinlei Chen; Saining Xie et al. | cvpr | 2022-06-07 |
| 4 | Masked-Attention Mask Transformer for Universal Image Segmentation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We present Masked-attention Mask Transformer (Mask2Former), a new architecture capable of addressing any image segmentation task (panoptic, instance or semantic). | Bowen Cheng; Ishan Misra; Alexander G. Schwing et al. | cvpr | 2022-06-07 |
| 5 | Depth-Supervised NeRF: Fewer Views and Faster Training for Free IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: One potential reason is that standard volumetric rendering does not enforce the constraint that most of a scene's geometry consist of empty space and opaque surfaces. We formalize the above assumption through DS-NeRF (Depth-supervised Neural Radiance Fields), a loss for learning radiance fields that takes advantage of readily-available depth supervision. | Kangle Deng; Andrew Liu; Jun-Yan Zhu et al. | cvpr | 2022-06-07 |
This page lists the papers of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022), ordered by impact or potential impact.