liuziwei7

ANGIE

Code for "Audio-Driven Co-Speech Gesture Video Generation" (NeurIPS 2022, Spotlight Presentation).

UNIF

[ECCV 2022] The official repo for the paper "UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation".

EVA3D

[ICLR 2023 Spotlight] EVA3D: Compositional 3D Human Generation from 2D Image Collections

TripleE-DG

MotionDiffuse

MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model

on-device-dg

On-Device Domain Generalization

StyleSwap

StyleSwap: Style-Based Generator Empowers Robust Face Swapping (ECCV 2022)

Text2Light

[SIGGRAPH Asia 2022] Text2Light: Zero-Shot Text-Driven HDR Panorama Generation

VToonify

[SIGGRAPH Asia 2022] VToonify: Controllable High-Resolution Portrait Video Style Transfer

xrmogen

OpenXRLab Multi-Modal Motion Generation Toolbox and Benchmark

xrmocap

OpenXRLab Multi-view Motion Capture Toolbox and Benchmark

hmr-benchmarks

AnimeRun

API for AnimeRun dataset

StyleKD

[ECCV2022] Mind the Gap in Distilling StyleGANs

StyleFaceV

Code for StyleFaceV

StyleLight

[ECCV 2022] StyleLight: HDR Panorama Generation for Lighting Estimation and Editing

CelebV-HQ

[ECCV 2022] CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

OpenPSG

Benchmarking Panoptic Scene Graph Generation (PSG), ECCV'22

Relighting4D

[ECCV 2022] Relighting4D: Neural Relightable Human from Videos

OmniBenchmark

[ECCV2022] New benchmark for evaluating pre-trained model; New supervised contrastive learning framework.

fast-vid2vid

The code for ECCV22 paper "Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis"

CelebA-Dialog

A large-scale visual-language face dataset with fine-grained annotations (ICCV 2021)

LaserMix

[CVPR 2023 Highlight] LaserMix for Semi-Supervised LiDAR Semantic Segmentation

SeqDeepFake

[ECCV 2022] PyTorch code for SeqDeepFake: Detecting and Recovering Sequential DeepFake Manipulation

PointCloud-C

Benchmarking and Analyzing Point Cloud Perception Robustness under Corruptions

NOAH

Searching prompt modules for parameter-efficient transfer learning.

Generalizable-Mixture-of-Experts

GMoE could be the next backbone model for many kinds of generalization task.

DeepFashion-MultiModal

A large-scale high-quality human dataset with rich multi-modal annotations

Text2Human

Code for Text2Human (SIGGRAPH 2022). Paper: Text2Human: Text-Driven Controllable Human Image Generation

DistillingSelf

MICCAI 2022: Free Lunch for Surgical Video Understanding by Distilling Self-Supervisions