Канал: RWTHVision

ControlRoom3D: Room Generation using Semantic Controls [CVPR'24]

ControlRoom3D: Room Generation using Semantic Controls [CVPR'24]

TarViS: A Unified Approach for Target-based Video Segmentation (CVPR'23 Highlight)

TarViS: A Unified Approach for Target-based Video Segmentation (CVPR'23 Highlight)

Mask3D: Mask Transformer for 3D Instance Segmentation (ICRA'23)

Mask3D: Mask Transformer for 3D Instance Segmentation (ICRA'23)

BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video

BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video

Learning 3D Human Pose Estimation from Dozens of Datasets by Bridging Skeleton Formats (WACV'23)

Learning 3D Human Pose Estimation from Dozens of Datasets by Bridging Skeleton Formats (WACV'23)

HODOR: High-Level Object Descriptors for Object Resegmentation in Video From Static Images (CVPR'22)

HODOR: High-Level Object Descriptors for Object Resegmentation in Video From Static Images (CVPR'22)

ECCV'22 Demo: Accurate and Efficient Absolute 3D Human Pose Estimation Trained on Dozens of Datasets

ECCV'22 Demo: Accurate and Efficient Absolute 3D Human Pose Estimation Trained on Dozens of Datasets

Mix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV'21 Oral)

Mix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV'21 Oral)

MeTRAbs + EfficientNetV2 = Robust Absolute 3D Human Pose (Qualitative Teaser)

MeTRAbs + EfficientNetV2 = Robust Absolute 3D Human Pose (Qualitative Teaser)

CVPR Robust Video Scene Understanding Workshop

CVPR Robust Video Scene Understanding Workshop

From Points to Multi-Object 3D Reconstruction [CVPR 2021]

From Points to Multi-Object 3D Reconstruction [CVPR 2021]

Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera (ICRA'21)

Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera (ICRA'21)

MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation

MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation

DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data

DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data

Making a Case for 3D Convolutions for Object Segmentation in Videos (BMVC'20)

Making a Case for 3D Convolutions for Object Segmentation in Videos (BMVC'20)

Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections - ECCV2020

Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections - ECCV2020

STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos (ECCV'20)

STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos (ECCV'20)

5th BMTT MOTChallenge Workshop: Multi-Object Tracking and Segmentation

5th BMTT MOTChallenge Workshop: Multi-Object Tracking and Segmentation

Reposing Humans by Warping 3D Features (CVPRW'20)

Reposing Humans by Warping 3D Features (CVPRW'20)

DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes (CVPR'20 Oral)

DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes (CVPR'20 Oral)

3D MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation (CVPR'20)

3D MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation (CVPR'20)

Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds

Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds

Detection-Tracking for Efficient Person Analysis: The DetTA Pipeline

Detection-Tracking for Efficient Person Analysis: The DetTA Pipeline

CAMOT: Category-Agnostic Vision-based Multi-Object Tracking

CAMOT: Category-Agnostic Vision-based Multi-Object Tracking

Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds

Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds

DROW: Real-Time Deep Learning based Wheelchair Detection in 2D Range Data

DROW: Real-Time Deep Learning based Wheelchair Detection in 2D Range Data

Full-Resolution Residual Networks (FRRNs) for Semantic Image Segmentation in Street Scenes

Full-Resolution Residual Networks (FRRNs) for Semantic Image Segmentation in Street Scenes

Joint Object Pose Estimation and Shape Reconstruction in Urban Street Scenes Using 3D Shape Priors

Joint Object Pose Estimation and Shape Reconstruction in Urban Street Scenes Using 3D Shape Priors