Pinned Repositories
adaptis
[ICCV19] AdaptIS: Adaptive Instance Selection Network, https://arxiv.org/abs/1909.07829
fbrs_interactive_segmentation
[CVPR2020] f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation https://arxiv.org/abs/2001.10331
fcaf3d
[ECCV2022] FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection
image_harmonization
[WACV2021] Foreground-aware Semantic Representations for Image Harmonization https://arxiv.org/abs/2006.00809
imvoxelnet
[WACV2022] ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection
iterdet
[S+SSPR2020] IterDet: Iterative Scheme for Object Detection in Crowded Environments
NeuralHaircut
Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction. ICCV 2023
pytorch-ensembles
Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning, ICLR 2020
ritm_interactive_segmentation
Reviving Iterative Training with Mask Guidance for Interactive Segmentation
rome
Realistic mesh-based avatars. ECCV 2022
SamsungLabs's Repositories
SamsungLabs/FineControlNet
Official Pytorch Implementation of "FineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injection", 2023
SamsungLabs/SPIn-NeRF
3D Scene Inpainting with NeRFs
SamsungLabs/SummaryMixing
This repository implements SummaryMixing, a simpler, faster and much cheaper replacement to self-attention for automatic speech recognition (see: https://arxiv.org/abs/2307.07421). The code is ready to be used with the SpeechBrain toolkit).
SamsungLabs/hifi_plusplus
HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement (ICASSP 2023)
SamsungLabs/RAMP
[IROS 2023] RAMP: Hierarchical Reactive Motion Planning for Manipulation Tasks Using Implicit Signed Distance Functions
SamsungLabs/HIO-SDF
[ICRA 2024] HIO-SDF: Hierarchical Incremental Online Signed Distance Fields
SamsungLabs/SceneGrasp
[IROS 2023] Real-time Simultaneous Multi-Object 3D Shape Reconstruction, 6DoF Pose Estimation and Dense Grasp Prediction
SamsungLabs/W2E
This is a project of "Cybersecurity Event Detection with New and Re-emerging Words". (ASIACCS 2020)
SamsungLabs/awesomeyaml
Utility library to help parsing, transforming and querying yaml-based configs
SamsungLabs/hierarchical-act
This supplementary code is for IROS 2024 paper "Hierarchical Action Chunk Transformer: Learning Temporal Multimodality from Demonstrations with Fast Imitation Behavior"
SamsungLabs/c2g-HOF
[ICRA 2021, IROS 2021] Cost-to-Go Function Generating Networks for High Dimensional Motion Planning
SamsungLabs/ShellRecontruction
[IROS 2022] Object Shell Reconstruction: Camera-centric Object Representation for Robotic Grasping
SamsungLabs/myQASR
Open source the codebase related to the paper: E. Fish, U. Michieli, M. Ozay, "A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization", 2023. The paper has been accepted for publication at the INTERSPEECH 2023 Conference.
SamsungLabs/FineControlNet-project-page
Project webpage of "FineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injection", 2023
SamsungLabs/RIC
RIC: Rotate-Inpaint-Complete for Generalizable Scene Reconstruction
SamsungLabs/NASR
SamsungLabs/AdaCLIP
This repository contains the code for AdaCLIP, a computation and latency-aware system for pragmatic multimodal video retrieval.
SamsungLabs/Z-Fold
Official Implementation of "Z-Fold: A Frustratingly Easy Post-Training Quantization Scheme for LLMs" (EMNLP 2023)
SamsungLabs/FROST
Codebase release for our accepted paper at ICASSP 2024.
SamsungLabs/HandNeRF-project-page
Project webpage of "HandNeRF: Learning to Reconstruct Hand-Object Interaction Scene from a Single RGB Image", ICRA 2024
SamsungLabs/HIO-SDF-project-page
Project page for "HIO-SDF: Hierarchical Incremental Online Signed Distance Fields"
SamsungLabs/viola-project-page
Project webpage for "VioLA: Aligning Videos to 2D LiDAR Scans"
SamsungLabs/WatchYourSteps
3D scenes editing using NeRFs
SamsungLabs/RIC-project-page
RIC: Rotate-Inpaint-Complete for Generalizable Scene Reconstruction
SamsungLabs/c2g-HOF-project-page
[ICRA 2021, IROS 2021] Cost-to-Go Function Generating Networks for High Dimensional Motion Planning
SamsungLabs/GePSAN
Official implementation of method proposed in: Abdelsalam, Mohamed A., et al. "GePSAn: Generative Procedure Step Anticipation in Cooking Videos." Proceedings of th
SamsungLabs/RefGuided3DInpainting
Reference guided 3D scene inpainting
SamsungLabs/SA4-AIML
GitHub for Samsung SA4 FS_AI4Media Evaluation
SamsungLabs/SceneGrasp-project-page
SceneGrasp Project Page
SamsungLabs/SyMPIE
Release the code of our published paper at ACM MMSys 2024 conference.