Infinite Photorealistic Worlds using Procedural Generation

Official Implementation of paper "A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence"

VFDepth Self-supervised surround-view depth estimation with volumetric feature fusion

[TPAMI'23] Unifying Flow, Stereo and Depth Estimation

Convert Machine Learning Code Between Frameworks

Semi-supervised optical flow network

[CVPR'22] NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

[ECCV'20] Convolutional Occupancy Networks

[CVPR 2022 Oral & TPAMI 2023] Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion

This is the open source implementation of the ICLR2022 paper "StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis"

BANMo Building Animatable 3D Neural Models from Many Casual Videos

FILM: Frame Interpolation for Large Motion, In ECCV 2022.

Code for "Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses"

Self-supervised temporally consistent depth estimation

PyTorch implementation of Superpixel Sampling Networks

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

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

OpenMMLab optical flow toolbox and benchmark

Dense Unsupervised Learning for Video Segmentation (NeurIPS*2021)

Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)

Code release for "COTR: Correspondence Transformer for Matching Across Images"(ICCV 2021)

PyTorch Lightning Optical Flow models, scripts, and pretrained weights.

Related papers and codes for vision-based robotic grasping