StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)

4DHumans: Reconstructing and Tracking Humans with Transformers

This repository provides motion datasets collected by Bandai Namco Research Inc

Official implementation of AnimateDiff.

Neural Rendering with Attention: An Incremental Improvement for Anime Character Animation

Open-sourced dataset of CoNR

Training code for "SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation"

IJCAI2023 - Collaborative Neural Rendering using Anime Character Sheets

Dynamic Neural Radiance Fields for Monocular 4D Facial Avater Reconstruction

HumanNeRF turns a monocular video of moving people into a 360 free-viewpoint video.

[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

WACV2022: Transfer Learning for Pose Estimation of Illustrated Characters

Instance segmentation for anime characters based on CondInst and SOLOv2

Papers, repository and other data about anime or manga research. Please let me know if you have information that the list does not include.

Anime Face Detector using mmdet and mmpose

(WACV 2022) Estimating Image Depth in the Comics Domain

COLMAP - Structure-from-Motion and Multi-View Stereo

Code base for D++ with suggested counterfactual partners

Repository for the multi-rover exploration domain. Contains barebones rover domain, neuro-evolutionary learning facilitated through a CCEA, and basic reward functions for learning.

Repository contains PhD Dissertation research code involving counterfactual learning and adaptation in the multi-rover exploration problem.