astra-vision / DenseMTLLinks
Cross-task Attention Mechanism for Dense Multi-task Learning (WACV 2023)
☆51Updated 2 years ago
Alternatives and similar repositories for DenseMTL
Users that are interested in DenseMTL are comparing it to the libraries listed below
Sorting:
- [Preprint 2022] “Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer?” by Yi Wang, Zhiwen Fan, Tianlong Chen, Hehe Fan, Zh…☆63Updated 2 years ago
- [ECCV 2022] Masked Discrimination for Self-Supervised Learning on Point Clouds☆95Updated 3 years ago
- Learning with Noisy Labels for Robust Point Cloud Segmentation (ICCV2021 Oral)☆67Updated 2 years ago
- CVPR 2021 Oral https://arxiv.org/abs/2104.02243☆47Updated last year
- [CVPR2023] This is an official implementation for "PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes".☆107Updated 2 years ago
- [ECCV 2022] Official pytorch implementation of the paper, "PointMixer: MLP-Mixer for Point Cloud Understanding"☆108Updated last year
- PyTorch NYUv2 Dataset Class☆90Updated 2 years ago
- Official implementation for [3DV 2024] `Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding`☆47Updated last year
- Gradient-based Uncertainty for Monocular Depth Estimation (ECCV 2022)☆50Updated 2 years ago
- Official implementation of "WorDepth: Variational Language Prior for Monocular Depth Estimation"☆41Updated 8 months ago
- [ICCV'21] Pri3D: Can 3D Priors Help 2D Representation Learning?☆149Updated 3 years ago
- a Pytorch library for multi-view 3D understanding and generation☆83Updated 9 months ago
- [ECCV2022] 3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling☆17Updated 3 years ago
- Official PyTorch implementation of TransforMatcher: Match-to-Match Attention for Semantic Correspondence (CVPR 2022 Poster)☆39Updated 2 years ago
- Official implementation of "Can Language Understand Depth?"☆81Updated 2 years ago
- Official implementation for ECCV 2022 paper "3D Instances as 1D Kernels".☆56Updated 2 years ago
- [NeurIPS 2022 Spotlight] P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting☆129Updated 2 years ago
- (ECCV 2022) DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation☆49Updated 2 years ago
- Semantic Scene Completion☆108Updated 5 years ago
- Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding (ICLR 2023)☆21Updated 2 years ago
- official implementation for our ICCV 2019 paper : Voxel VAE Net with Group Convolutions for Point Cloud Segmentation☆19Updated 2 years ago
- PyTorch Implementation of FlowNet3D (https://arxiv.org/pdf/1806.01411.pdf)☆15Updated 5 years ago
- An implementation of our work "Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation".☆36Updated 4 years ago
- [NeurIPS 2022] 4D Unsupervised Object Discovery☆56Updated last year
- Official implementation of Image2Point.☆125Updated 2 years ago
- Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks☆110Updated 2 years ago
- ☆56Updated 10 months ago
- Toolkit for VIPER benchmark☆14Updated 5 years ago
- The code of 'Towards Domain-agnostic depth completion'☆27Updated 3 years ago
- [AAAI 2023] MOVEDepth: Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learning☆61Updated 3 years ago