[ICCV23] Official Implementation of CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation

[CVPR2023] CompletionFormer: Depth Completion with Convolutions and Vision Transformers

A novel paradigm for collecting and generating stereo training data using neural rendering

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

[NeurIPS 2023] RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

[CVPR2023] This is an official implementation for "PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes".

[ICCV 2023] Official implementation of "SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields"

Code release for ConvNeXt V2 model

EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]

Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images

Official Implementation of Semantic Image Synthesis via Diffusion Models

[CVPR2023] Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation

This repository contains the source code for our paper: MODE: Multi-view Omnidirectional Depth Estimation with 360-degree Cameras. ECCV 2022

Code for "Deconstructing Monocular Depth Reconstruction: The Design Decisions that Matter" (https://arxiv.org/abs/2208.01489)

[ECCV 2022] Official repository for "MaxViT: Multi-Axis Vision Transformer". SOTA foundation models for classification, detection, segmentation, image quality, and generative modeling...

Label-Efficient Semantic Segmentation with Diffusion Models (ICLR'2022)

Official PyTorch implementation of MonoDEVSNet - "Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision."

🐍 Geometric Computer Vision Library for Spatial AI

Robust Vision Challenge Devkits

Lite Vision Transformer (CVPR 2022)

Self-Supervised depth kalilia

[ECCV2022] RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation

[ NeurIPS2021] This is an official implementation of our paper "HRFormer: High-Resolution Transformer for Dense Prediction".

Official implementation of PVT series

Reproduction of the CVPR 2020 paper - Self-supervised monocular trained depth estimation using self-attention and discrete disparity volume