[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

This repository contains the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"

[CVPR 2021] Multi-Stage Progressive Image Restoration. SOTA results for Image deblurring, deraining, and denoising.

(CVPR 2021 Oral) Open World Object Detection

Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)

[CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers

[CVPR 2021 Best Student Paper Honorable Mention, Oral] Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks.

💭 Diffusion Probabilistic Models for 3D Point Cloud Generation (CVPR 2021)

[CVPR 2021] Self-supervised depth estimation from short sequences

Official implementation of the paper: MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera (CVPR 2021)

[CVPR 2021] VirTex: Learning Visual Representations from Textual Annotations

Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021 Oral.

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]

[CVPR 2021] CPS: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection, CVPR2021

[TPAMI 2022 & CVPR2021 Oral] UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion. Semi-supervised VOS as well!

[CVPR21] LightTrack: Finding Lightweight Neural Network for Object Tracking via One-Shot Architecture Search

💄 Lipstick ain't enough: Beyond Color-Matching for In-the-Wild Makeup Transfer (CVPR 2021)

[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition