46 Open source projects that are alternatives of or similar to PoinTr

(TPAMI 2022) Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer

[ICCV'21] PlaneTR: Structure-Guided Transformers for 3D Plane Recovery

MVP Benchmark for Multi-View Partial Point Cloud Completion and Registration

Code and models for ICCV2021 paper "Robust Object Detection via Instance-Level Temporal Cycle Confusion".

Vision-Language Transformer and Query Generation for Referring Segmentation (ICCV 2021)

[ ICCV 2021 Oral ] Our method can estimate camera poses and neural radiance fields jointly when the cameras are initialized at random poses in complex scenarios (outside-in scenes, even with less texture or intense noise )

[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.

ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models (ICCV 2021 Oral)

[ICCV'21] Official PyTorch implementation of Relational Embedding for Few-Shot Classification

ICCV2021/2019/2017 论文/代码/解读/直播合集，极市团队整理

[NeurIPS 2021] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

🤗🖼️ HuggingPics: Fine-tune Vision Transformers for anything using images found on the web.

Official repository for the ShapeFormer Project

Pose Correction for Highly Accurate Visual Localization in Large-scale Indoor Spaces (ICCV 2021)

EsViT: Efficient self-supervised Vision Transformers

3DV 2021: Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry

code for our ICCV 2021 paper "DeepCAD: A Deep Generative Network for Computer-Aided Design Models"

[ICCV21] Code for "RetrievalFuse: Neural 3D Scene Reconstruction with a Database"

A curated list of awesome Single-view 3D Object Reconstruction papers & resources

Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer

[ICCV2021] Learning to Track Objects from Unlabeled Videos

Spatial-Temporal Transformer for Dynamic Scene Graph Generation, ICCV2021

Mix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV 2021 Oral)

[ICCV 2021] TRAR: Routing the Attention Spans in Transformers for Visual Question Answering -- Official Implementation

This paper is accepted by ICCV 2021.

[IROS, 2020] Indoor Scene Recognition in 3D

Parametric Contrastive Learning (ICCV2021)

Reference code for the paper "Cross-Camera Convolutional Color Constancy" (ICCV 2021)

[ICCV 2021 Oral] High-Resolution Optical Flow from 1D Attention and Correlation

[ICCV 2021] InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring

Official implementation of deep matching prior

Official implementation of MSR-GCN (ICCV2021 paper)

LLVIP: A Visible-infrared Paired Dataset for Low-light Vision

code for our ICCV 2021 paper 'Generalized Source-free Domain Adaptation'

Library - Vanilla, ViT, DeiT, BERT, GPT

[ICCV 2021 Oral] NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo

Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM

[NeurIPS'21] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

A Collection of Papers and Codes for ICCV2021 Low Level Vision and Image Generation

Meta Self-learning for Multi-Source Domain Adaptation： A Benchmark

[ICCV'21] NEAT: Neural Attention Fields for End-to-End Autonomous Driving

(ICCV 2021) Code for "Unsupervised Layered Image Decomposition into Object Prototypes" paper

Official implementation of "Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis", ICCV 2021

Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)

Official implementation of "Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform", ICCV 2021

Official code release for ICCV 2021 paper SNARF: Differentiable Forward Skinning for Animating Non-rigid Neural Implicit Shapes.