ritm_interactive_segmentation
Reviving Iterative Training with Mask Guidance for Interactive Segmentationfbrs_interactive_segmentation
[CVPR2020] f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation https://arxiv.org/abs/2001.10331NeuralHaircut
Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction. ICCV 2023rome
Realistic mesh-based avatars. ECCV 2022adaptis
[ICCV19] AdaptIS: Adaptive Instance Selection Network, https://arxiv.org/abs/1909.07829imvoxelnet
[WACV2022] ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectionimage_harmonization
[WACV2021] Foreground-aware Semantic Representations for Image Harmonization https://arxiv.org/abs/2006.00809pytorch-ensembles
Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning, ICLR 2020fcaf3d
[ECCV2022] FCAF3D: Fully Convolutional Anchor-Free 3D Object Detectioniterdet
[S+SSPR2020] IterDet: Iterative Scheme for Object Detection in Crowded EnvironmentsFineControlNet
Official Pytorch Implementation of "FineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injection", 2023SPIn-NeRF
3D Scene Inpainting with NeRFsTwiTi
This is a project of "#Twiti: Social Listening for Threat Intelligence" (TheWebConf 2021)zero-cost-nas
Zero-Cost Proxies for Lightweight NASBayesDLL
tr3d
[ICIP2023] TR3D: Towards Real-Time Indoor 3D Object DetectionASAM
Implementation of ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks, ICML 2021.MLI
Novel View Synthesis with multiplane/multilayer representation: CVPR2022, WACV2023td3d
[WACV'24] TD3D: Top-Down Beats Bottom-Up in 3D Instance Segmentationday-to-night
saic_depth_completion
Official implementation of "Decoder Modulation for Indoor Depth Completion" https://arxiv.org/abs/2005.08607Butterfly_Acc
The codes and artifacts associated with our MICRO'22 paper titled: "Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design"DINAR
Inference code for "DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatars"tqc_pytorch
Implementation of Truncated Quantile Critics method for continuous reinforcement learning. https://bayesgroup.github.io/tqc/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).style-people
Inference code for "StylePeople: A Generative Model of Fullbody Human Avatars" paperMTL
RAMP
[IROS 2023] RAMP: Hierarchical Reactive Motion Planning for Manipulation Tasks Using Implicit Signed Distance Functionsffc_se
Code for the paper "FFC-SE: Fast Fourier Convolution for Speech Enhancement" (published at Interspeech 2022 conference)hifi_plusplus
HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement (ICASSP 2023)deep-weight-prior
The Deep Weight Prior, ICLR 2019odometry
Training Deep SLAM on Single Frames https://arxiv.org/abs/1912.05405eagle
Measuring and predicting on-device metrics (latency, power, etc.) of machine learning modelspoint_based_clothing
Official PyTorch implementation of ICCV'21 paper Point-Based Modeling of Human ClothingHandNeRF
Official Pytorch Implementation of "HandNeRF: Learning to Reconstruct Hand-Object Interaction Scene from a Single RGB Image", ICRA 2024HIO-SDF
[ICRA 2024] HIO-SDF: Hierarchical Incremental Online Signed Distance Fieldsgps-augment
Simple but high-performing method for learning a policy of test-time augmentationNoise2NoiseFlow
cloud_transformers
[ICCV, 2021] Cloud Transformers: A Universal Approach To Point Cloud Processing Tasks https://arxiv.org/abs/2007.11679SceneGrasp
[IROS 2023] Real-time Simultaneous Multi-Object 3D Shape Reconstruction, 6DoF Pose Estimation and Dense Grasp PredictionSparse-Multi-DNN-Scheduling
Open-source artifacts and codes of our MICRO'23 paper titled “Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads”.Drop-DTW
ltmnet
Learning Tone Curves for Local Image Enhancementsemi-supervised-NFs
Code for the paper Semi-Conditional Normalizing Flows for Semi-Supervised LearningW2E
This is a project of "Cybersecurity Event Detection with New and Re-emerging Words". (ASIACCS 2020)FastFlow
FastFlow is a system that automatically detects CPU bottlenecks in deep learning training pipelines and resolves the bottlenecks with data pipeline offloading to remote resources .geometry-preserving-de
Towards General Purpose, Geometry Preserving Single-View Depth Estimation https://arxiv.org/abs/2009.12419neural-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.graphics2raw
Code associated with our paper "Graphics2RAW: Mapping Computer Graphics Images to Sensor RAW Images". The paper has been accepted to the International Conference on Computer Vision (ICCV'23).nb-asr
FACaP
[IROS 2022]Floorplan-Aware Camera Poses Refinementcontent-aware-metadata
coordinate_based_inpainting
[CVPR2019] Coordinate-based texture inpainting for pose-guided human image generation https://arxiv.org/abs/1811.11459Genie
Official Implementation of "Genie: Show Me the Data for Quantization" (CVPR 2023)blox
Macro Neural Architecture Search BenchmarkStepFormer
hierarchical-act
This supplementary code is for IROS 2024 paper "Hierarchical Action Chunk Transformer: Learning Temporal Multimodality from Demonstrations with Fast Imitation Behavior"Undiff
Test code disclosure for the research paper "UnDiff: Unsupervised Voice Restoration with Unconditional Diffusion Model", as a supplementary material for the paper accepted to the upcoming Interspeech2023 conference.EdgeViTs
[ECCV 2022] EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformersgenren
Implementation of 2D-3D Cyclic Generative Renderer (3DV-2020).awesomeyaml
Utility library to help parsing, transforming and querying yaml-based configspyworkers
Abstraction over threading, multiprocessing and TCP-based RPCShellRecontruction
[IROS 2022] Object Shell Reconstruction: Camera-centric Object Representation for Robotic GraspingStereoLayers
PALinux
In-Kernel Control-Flow Integrity on Commodity OSes using ARM Pointer Authenticationc2g-HOF
[ICRA 2021, IROS 2021] Cost-to-Go Function Generating Networks for High Dimensional Motion Planningtwo-camera-white-balance
hole-robust-wf
Data and code for the WACV 2022 paper, "Hole-robust Wireframe Detection"video-retrieval-sampler
The official implementation for the paper 'mmSampler: Efficient Frame Sampler for Multimodal Video Retrieval'.ordered_dropout
Technique of Ordered Dropout as used in the paper "Fjord: Fair and accurate federated learning under heterogeneous targets with ordered dropout", NeurIPS'21myQASR
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.FedorAS
FedorAS: Federated Architecture Search under system heterogeneityAdaCLIP
This repository contains the code for AdaCLIP, a computation and latency-aware system for pragmatic multimodal video retrieval.prime-count
This repository contains codes for Prime+Count paper.appbuddy
RIC
RIC: Rotate-Inpaint-Complete for Generalizable Scene ReconstructionX-MRS
Food image / recipe (text) cross-modal representation learning, retrieval and (image) synthesis. Code from ACM-Multimedia 2021 "Cross-Modal Retrieval and Synthesis (X-MRS): Closing the Modality Gap in Shared Representation Learning"FineControlNet-project-page
Project webpage of "FineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injection", 2023RGBD-FGN
RGBD Fusion Grasp Network with Large-Scale Tableware Grasp Datasetsmoke-bomb
SmokeBomb: Effective Mitigation Method against Cache Side-channel Attacks on the ARM Architecturefastflow-tensorflow
A customized Tensorflow with partial offloading and profiling features for FastFlow project.NASR
Z-Fold
Official Implementation of "Z-Fold: A Frustratingly Easy Post-Training Quantization Scheme for LLMs" (EMNLP 2023)procedure-planning
NAFLD
Two-dimensional convolutional neural network using quantitative US for non-invasive assessment of hepatic steatosis in NAFLDtranspr
ExpandersPruning
This respository contains the code and experiments for the paper "Data-Free Model Pruning at Initialization via Expanders", appearing at the Efficient Deep Learning for Computer Vision CVPR Workshop, 2023. Authors: James Stewart, Umberto Michieli, and Mete Ozay.NB-MLM
SAGE
WatchYourSteps
3D scenes editing using NeRFssaic-is
MotionID
MoRF-project-page
Multitask-RFG
Code to reproduce experiments for End-to-end recipe flow graph parsingviola-project-page
Project webpage for "VioLA: Aligning Videos to 2D LiDAR Scans"Metis
[ATC '24] Metis: Fast automatic distributed training on heterogeneous GPUs (https://www.usenix.org/conference/atc24/presentation/um)SwissDINO
Code release of our paper: "Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search"; Kirill Paramonov, Jia-Xing Zhong, Umberto Michieli, Jijoong Moon, Mete Ozay; IROS 2024.iiTransformer
Code for "iiTransformer: A Unified Approach to Exploiting Local and Non-Local Information for Image Restoration" (Kang et al., BMVC 2022)FROST
Codebase release for our accepted paper at ICASSP 2024.HandNeRF-project-page
Project webpage of "HandNeRF: Learning to Reconstruct Hand-Object Interaction Scene from a Single RGB Image", ICRA 2024Love Open Source and this site? Check out how you can help us