End-to-end SFM framework based on GTSAM

Making Structure-from-Motion (COLMAP) more robust to symmetries and duplicated structures

🚪✊Knock Knock: Get notified when your training ends with only two additional lines of code

Code for "FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent" by Cameron Smith*, David Charatan*, Ayush Tewari, and Vincent Sitzmann

A user-friendly and high-performance implementation of neural radiance fields (NeRF)

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

Official implementation of "Contrastive Audio-Language Learning for Music" (ISMIR 2022)

Easily compute clip embeddings from video frames

[ECCV'22 Oral] Towards Grand Unification of Object Tracking

Pen and paper exercises in machine learning

[CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation"

Official code for "Decoupling Zero-Shot Semantic Segmentation"

PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation （CVPR2022）

Real-time Object Detection for Streaming Perception, CVPR 2022

[CVPR 2022 (oral)] Bongard-HOI for benchmarking few-shot visual reasoning

[TPAMI 2023] Multimodal Image Synthesis and Editing: The Generative AI Era

Code for "OnePose: One-Shot Object Pose Estimation without CAD Models", CVPR 2022

Easy-to-use Face Analysis Tool

🧮 A collection of resources to learn mathematics for machine learning

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

[CVPR 2022] Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization

Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)

CLIPort: What and Where Pathways for Robotic Manipulation

The official implementation for Pseudo Numerical Methods for Diffusion Models on Manifolds (PNDM, PLMS | ICLR2022)

Transformer Tracking with Cyclic Shifting Window Attention (CSWinTT)

Language Models Can See: Plugging Visual Controls in Text Generation

Research code for CVPR 2022 paper "SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning"

A Non-Autoregressive End-to-End Text-to-Speech (text-to-wav), supporting a family of SOTA unsupervised duration modelings. This project grows with the research community, aiming to achieve the ulti…

[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.

Repo for external large-scale work