65: CIPS-3D

CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis by Peng Zhou et al. explained in 5 minutes

»
Author's profile picture Kirill Demochkin on 3D-aware-GAN-based-on-CIPS-and-NeRF

64: Sensorium

Harnessing the Conditioning Sensorium for Improved Image Translation by Nederhood et al. explained in 5 minutes

»
Author's profile picture Kirill Demochkin on multimodal-style-conditioned-image-to-image-domain-translation

63: LaMa

Resolution-robust Large Mask Inpainting with Fourier Convolutions by Suvorov et al. explained in 5 minutes

»
Author's profile picture Kirill Demochkin on large-masks-fourier-convolutions-inpainting

62: StyleNeRF

StyleNeRF by Anonymous ICLR 2022 submission explained in 5 minutes.

»
Author's profile picture Kirill Demochkin on unsupervised-discovery-nonlinear-latent-editing-directions-generator

61: WarpedGANSpace

WarpedGANSpace: Finding non-linear RBF paths in GAN latent space by Tzeplis et al. explained in 5 minutes.

»
Author's profile picture Kirill Demochkin on unsupervised-discovery-nonlinear-latent-editing-directions-generator

60: Unsupervised Discovery of GAN Directions

Unsupervised Discovery of Interpretable Directions in the GAN Latent Space by Voynov and Babenko explained in 5 minutes.

»
Author's profile picture Kirill Demochkin on unsupervised-discovery-editing-directions-gan-latent-space

59: ISF-GAN

ISF-GAN: An Implicit Style Function for High-Resolution Image-to-Image Translation by Yahui Liu et al. explained in 5 minutes.

»
Author's profile picture Kirill Demochkin on unsupervised_latent_space_exploration_image_to_image_GAN_editing

58: VGPNN

Diverse Generation from a Single Video Made Possible by Niv Haim, Ben Feinstein et al. explained in 5 minutes.

»
Author's profile picture Kirill Demochkin on patch-matching-single-video-input-diverse-video-generation

57: IC-GAN

Instance-Conditioned GAN by Arantxa Casanova et al. explained in 5 minutes.

»
Author's profile picture Kirill Demochkin on unaligned-image-class-conditional-generation

56: GSN

Unconstrained Scene Generation with Locally Conditioned Radiance Fields by Terrance DeVries et al. explained in 5 minutes.

»
Author's profile picture Kirill Demochkin on ICCV-2021-large-free-moving-indoor-scenes-NeRF

55: Object-NeRF

Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering by Bangbang Yang et al. explained in 5 minutes.

»
Author's profile picture Kirill Demochkin on multi-object-NeRF-3D-scene-editing

54: CLIP

Learning Transferable Visual Models From Natural Language Supervision by Alec Radford, Jong Wook Kim et al. explained in 5 minutes.

»
Author's profile picture Kirill Demochkin on zero-shot-contrastive-loss-image-text-pretraining

53: FLAN

Finetuned Language Models Are Zero-Shot Learners by Jason Wei et al. explained in 5 minutes.

»
Author's profile picture Kirill Demochkin on prompt-engineering-fine-tune-zero-shot-language-model

52: Robust Video Matting

Robust High-Resolution Video Matting with Temporal Guidance by Shanchuan Lin et al. explained in 5 minutes.

»
Author's profile picture Kirill Demochkin on cross-modal-fully-attentional-transformer

51: PerceiverIO

Perceiver IO: A General Architecture for Structured Inputs & Outputs by Andrew Jaegle et al. explained in 5 minutes.

»
Author's profile picture Kirill Demochkin on cross-modal-fully-attentional-transformer