Visual Understanding Lab @ Samsung AI Center Moscow

fbrs_interactive_segmentation

[CVPR2020] f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation https://arxiv.org/abs/2001.10331

adaptis

[ICCV19] AdaptIS: Adaptive Instance Selection Network, https://arxiv.org/abs/1909.07829

ritm_interactive_segmentation

Reviving Iterative Training with Mask Guidance for Interactive Segmentation

image_harmonization

[WACV2021] Foreground-aware Semantic Representations for Image Harmonization https://arxiv.org/abs/2006.00809

iterdet

[S+SSPR2020] IterDet: Iterative Scheme for Object Detection in Crowded Environments

imvoxelnet

[WACV2022] ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection

saic_depth_completion

Official implementation of "Decoder Modulation for Indoor Depth Completion" https://arxiv.org/abs/2005.08607

point_based_clothing

Official PyTorch code for the paper: "Point-Based Modeling of Human Clothing" (ICCV 2021)

style-people

Inference code for "StylePeople: A Generative Model of Fullbody Human Avatars" paper

odometry

Training Deep SLAM on Single Frames https://arxiv.org/abs/1912.05405

cloud_transformers

[ICCV, 2021] Cloud Transformers: A Universal Approach To Point Cloud Processing Tasks https://arxiv.org/abs/2007.11679

neural-textures

Inference code for "StylePeople: A Generative Model of Fullbody Human Avatars" paper. This code is for the part of the paper describing video-based avatars.

geometry-preserving-de

Towards General Purpose, Geometry Preserving Single-View Depth Estimation https://arxiv.org/abs/2009.12419

coordinate_based_inpainting

[CVPR2019] Coordinate-based texture inpainting for pose-guided human image generation https://arxiv.org/abs/1811.11459

GAN-high-resolution-representation