correct handin errors

approach.tex

@@ -265,13 +265,14 @@ l_{R}^k = \ell_{reg} (R_k^* - R_k),
 \begin{equation}
 l_{t}^k = \ell_{reg} (t_k^* - t_k),
 \end{equation}
+and
 \begin{equation}
-l_{p}^k = \ell_{reg} (p_k^* - p_k).
+l_{p}^k = \ell_{reg} (p_k^* - p_k)
 \end{equation}
 are the smooth-$\ell_1$ losses for the predicted rotation, translation and pivot,
 respectively and
 \begin{equation}
-l_o^k = \ell_{cls}(o_k, o_k^*).
+l_o^k = \ell_{cls}(o_k, o_k^*)
 \end{equation}
 is the (categorical) cross-entropy loss for the predicted classification into moving and non-moving objects.
 

experiments.tex

@@ -82,11 +82,16 @@ p_k^* = t_t^k
 and compute the ground truth object motion
 $\{R_k^*, t_k^*\} \in \mathbf{SE}(3)$ as
 \begin{equation}
-R_k^* = \mathrm{inv}(R_{cam}^*) \cdot R_{t+1}^k \cdot \mathrm{inv}(R_t^k),
+R_k^* = R_{t+1}^k \cdot R_{cam}^* \cdot \mathrm{inv}(R_t^k),
 \end{equation}
 \begin{equation}
-t_k^* = t_{t+1}^{k}  - R_k^* \cdot t_t^k.
+t_k^* = \mathrm{inv}(R_{cam}^*) \cdot t_{t+1}^{k} + t_{cam^{-1}}^* - R_k^* \cdot t_t^k,
 \end{equation}
+where
+\begin{equation}
+t_{cam^{-1}}^* = t_{t}^{ex}  - inv(R_{cam}^*) \cdot t_{t+1}^{ex}.
+\end{equation}
+
 
 As for the camera, we define $o_k^* \in \{ 0, 1 \}$,
 \begin{equation}