ICLR22 PointMLP Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
CVPR17 PointSetGeneration A Point Set Generation Network for 3D Object Reconstruction from a Single Image
CVPR19 GSPN GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud
NIPS21 Neural Scene Flow Prior
CVPR21 Flowstep3D FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation
21 Mask2Former Masked-attention Mask Transformer for Universal Image Segmentation
NIPS21 MaskFormer Per-Pixel Classification is Not All You Need for Semantic Segmentation
NIPS21 K-Net K-Net: Towards Unified Image Segmentation
CVPR21 DyStaB DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping
CVPR17 MR-Flow Optical Flow in Mostly Rigid Scenes
CVPR16 SOF Optical Flow With Semantic Segmentation and Localized Layers
CVPR13 FC-2Layers A Fully-Connected Layered Model of Foreground and Background Flow
CVPR12 nLayers Layered segmentation and optical flow estimation over time
NIPS10 Layers++ Layered Image Motion with Explicit Occlusions, Temporal Consistency, and Depth Ordering
22 Automatic Labeling to Generate Training Data for Online LiDAR-based Moving Object Segmentation
RAL21 LMNet Moving object segmentation in 3D LiDAR data: A learning-based approach exploiting sequential data
IROS19 SelfDeepMask Self-supervised Transfer Learning for Instance Segmentation through Physical Interaction
21 Equivalences Between Sparse Models and Neural Networks
NIPS20 MCR2 Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction
00 Information bottleneck The information bottleneck method
3DV21 PoseContrast PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning
ICCV21 DepthContrast Self-Supervised Pretraining of 3D Features on Any Point-Cloud
CVPR21 ContrastiveSceneContexts Exploring Data-Efficient 3D Scene Understanding With Contrastive Scene Contexts
NIPS20 InfoMin What Makes for Good Views for Contrastive Learning?
ECCV20 PointContrast PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
21 PPD Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objects
NIPS21 SIMONe SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition
ICCV21 InSeGAN InSeGAN: A Generative Approach to Segmenting Identical Instances in Depth Images
NIPS20 MulMON Learning Object-Centric Representations of Multi-Object Scenes from Multiple View
ICLR20 Genesis GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
ICCV19 BAE-Net BAE-NET: Branched Autoencoder for Shape Co-Segmentation