File size: 7,694 Bytes
15bc41b 9564652 d965e49 15bc41b 9564652 d965e49 15bc41b 9564652 d965e49 9564652 d965e49 9564652 6e677b9 d965e49 6e677b9 d965e49 6e677b9 d965e49 6e677b9 d965e49 9564652 d965e49 9564652 d965e49 9564652 d965e49 6e677b9 d965e49 9564652 6e677b9 d965e49 9564652 d965e49 9564652 d965e49 9564652 d965e49 6e677b9 9564652 6e677b9 d965e49 6e677b9 9564652 15bc41b d965e49 15bc41b d965e49 9564652 d965e49 6e677b9 d965e49 15bc41b 9564652 d965e49 9564652 6e677b9 d965e49 15bc41b 9564652 6e677b9 d965e49 6e677b9 d965e49 15bc41b 9564652 d965e49 9564652 15bc41b 9564652 d965e49 9564652 6e677b9 9564652 d965e49 6e677b9 d965e49 9564652 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 |
import gradio as gr
import os
import cv2
import numpy as np
from tqdm import tqdm
from moviepy.editor import *
import tempfile
import esim_py
from infererence import process_events, Ev2Hands
from settings import OUTPUT_HEIGHT, OUTPUT_WIDTH
ev2hands = Ev2Hands()
def create_video(frames, fps, path):
clip = ImageSequenceClip(frames, fps=fps)
clip.write_videofile(path, fps=fps)
return path
def get_frames(video_in, trim_in):
cap = cv2.VideoCapture(video_in)
fps = cap.get(cv2.CAP_PROP_FPS)
stop_frame = int(trim_in * fps)
print("video fps: " + str(fps))
frames = []
i = 0
while(cap.isOpened()):
ret, frame = cap.read()
if not ret:
break
frame = cv2.resize(frame, (OUTPUT_WIDTH, OUTPUT_HEIGHT))
frames.append(frame)
if i > stop_frame:
break
i += 1
cap.release()
return frames, fps
def change_model(model_slider, eventframe_files, mesh_files):
if mesh_files is None:
return None, None
if model_slider >= len(mesh_files):
model_slider = len(mesh_files)
idx = int(model_slider - 1)
event_frame_path = eventframe_files[idx]
mesh_path = mesh_files[idx]
return model_slider, event_frame_path, mesh_path
def infer(video_inp, trim_in, threshold):
if video_inp is None:
return None, None, None
frames, fps = get_frames(video_inp, trim_in)
ts_s = 1 / fps
ts_ns = ts_s * 1e9 # convert s to ns
POS_THRESHOLD = NEG_THRESHOLD = threshold
REF_PERIOD = 0
print(f'Threshold: {threshold}')
esim = esim_py.EventSimulator(POS_THRESHOLD, NEG_THRESHOLD, REF_PERIOD, 1e-4, True)
is_init = False
temp_folder = f'temp/{next(tempfile._get_candidate_names())}'
event_frame_folder = f'{temp_folder}/event_frames'
mesh_folder = f'{temp_folder}/meshes'
os.makedirs(event_frame_folder, exist_ok=True)
os.makedirs(mesh_folder, exist_ok=True)
mesh_paths = list()
event_frames = list()
for idx, frame in enumerate(tqdm(frames)):
frame_gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
frame_log = np.log(frame_gray.astype("float32") / 255 + 1e-4)
current_ts_ns = idx * ts_ns
if not is_init:
esim.init(frame_log, current_ts_ns)
is_init = True
continue
events = esim.generateEventFromCVImage(frame_log, current_ts_ns)
data = process_events(events)
mesh = ev2hands(data)
mesh_path = f'{mesh_folder}/{idx}.obj'
mesh.export(mesh_path)
mesh_paths.append(mesh_path)
event_frame = data['event_frame'].cpu().numpy().astype(dtype=np.uint8)
event_frame_path = f'{event_frame_folder}/{idx}.jpg'
cv2.imwrite(event_frame_path, event_frame)
event_frames.append(event_frame_path)
return event_frames, event_frames[0], mesh_paths, mesh_paths[0]
with gr.Blocks(css='style.css') as demo:
gr.Markdown(
"""
<div align="center">
<h1>Ev2Hands: 3D Pose Estimation of Two Interacting Hands from a Monocular Event Camera</h1>
</div>
"""
)
gr.Markdown(
"""
<div align="center">
<h4>
Note: The model's performance may be suboptimal as the Event Stream derived from the input video inadequately reflects the characteristics of an event stream generated by an event camera. 🚫📹
</h4>
</div>
"""
)
gr.Markdown(
"""
<p align="center">
<a title="Project Page" href="https://4dqv.mpi-inf.mpg.de/Ev2Hands/" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
<img src="https://img.shields.io/badge/Project-Website-5B7493?logo=googlechrome&logoColor=5B7493">
</a>
<a title="arXiv" href="https://arxiv.org/abs/2312.14157" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
<img src="https://img.shields.io/badge/arXiv-Paper-b31b1b?logo=arxiv&logoColor=b31b1b">
</a>
<a title="GitHub" href="https://github.com/Chris10M/Ev2Hands/" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
<img src="https://img.shields.io/github/stars/Chris10M/Ev2Hands?label=GitHub%20%E2%98%85&&logo=github" alt="badge-github-stars">
</a>
<a title="Video" href="https://youtu.be/nvES_c5vRfU" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
<img src="https://img.shields.io/badge/YouTube-Video-red?logo=youtube&logoColor=red">
</a>
<a title="Visitor" href="https://hits.seeyoufarm.com" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
<img src="https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fhuggingface.co%2Fspaces%2Fchris10%2Fev2hands&count_bg=%2379C83D&title_bg=%23555555&icon=&icon_color=%23E7E7E7&title=hits&edge_flat=false">
</a>
</p>
"""
)
with gr.Column(elem_id="col-container"):
# gr.HTML(title)
with gr.Row():
with gr.Column():
video_inp = gr.Video(label="Video source", elem_id="input-vid")
with gr.Row():
trim_in = gr.Slider(label="Cut video at (s)", minimum=1, maximum=5, step=1, value=1)
threshold = gr.Slider(label="Event Threshold", minimum=0.1, maximum=1, step=0.05, value=0.8)
gr.Examples(
examples=[os.path.join(os.path.dirname(__file__), "examples/video.mp4")],
inputs=video_inp,
)
with gr.Column():
eventframe_files = gr.Files(visible=False, label='Event frame paths')
mesh_files = gr.Files(visible=False, label='3D Mesh Files')
event_frame = gr.Image(label="Event Frame")
prediction_out = gr.Model3D(clear_color=[0.0, 0.0, 0.0, 0.0], label="Ev2Hands result")
model_slider = gr.Slider(minimum=1, step=1, label="Frame Number")
gr.HTML("""
<a style="display:inline-block" href="https://huggingface.co/spaces/chris10/ev2hands?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a>
work with longer videos / skip the queue:
""", elem_id="duplicate-container")
submit_btn = gr.Button("Run Ev2Hands")
inputs = [video_inp, trim_in, threshold]
outputs = [eventframe_files, event_frame, mesh_files, prediction_out]
submit_btn.click(infer, inputs, outputs)
model_slider.change(change_model, [model_slider, eventframe_files, mesh_files], [model_slider, event_frame, prediction_out])
demo.queue(max_size=12).launch(server_name="0.0.0.0", server_port=7860) |