add TLDR summary

app.py

@@ -45,7 +45,13 @@ phi = st.sidebar.slider("Phi", min_value=0., max_value=0.5*pi,
 radius = st.sidebar.slider("Radius", min_value=2., max_value=6.,
                            step=1., value=3.)
 
-with st.spinner("Generating the view..."):
+caption = "Diet-NeRF achieves SoTA few-shot learning capacity in 3D model reconstruction. " \
+          "Thanks to the 2D supervision by CLIP (aka semantic loss), " \
+          "it can render views that both challenging and novel with ONLY 8 training images, " \
+          "outperforming original NeRF!"
+st.markdown(f""" <h4> {caption} </h4> """,
+            unsafe_allow_html=True)
+with st.spinner("Rendering Image (may take 2-3 mins)..."):
     pred_color, _ = render_predict_from_pose(state, theta, phi, radius)
     im = predict_to_image(pred_color)