zerolover

Sure, I upload the simulated imu data and result to google drive~ Here is the [link](https://drive.google.com/drive/folders/1uL5PjEw4p6u7oR5QpOpGYhu5L5y3uVQS?usp=sharing) int imu_frequency = 200; // Hz double gyro_noise_sigma = 0.000224; // rad/s double gyro_bias_sigma...

replace https://github.com/LiJiangnanBit/path_optimizer/blob/5490467cd88bcf3c86b5355d16e9f5107e26bc18/CMakeLists.txt#L20 with `LIST(APPEND CMAKE_MODULE_PATH ${PROJECT_SOURCE_DIR}/cmake)`

edit config.yml at svlsimulator-linux64-2021.3 change `api_hostname: "localhost"` to `api_hostname: "*"` \# set host ip export LGSVL__SIMULATOR_HOST=192.168.1.x ./01-connecting-to-simulator.py

@ladzin after +0, screenspace_points.is_leaf = False, and we should add `screenspace_points.retain_grad()`

Yesterday I encountered the same problem but I don't know why until I found this issue. [source code here](https://github.com/isl-org/Open3D/blob/553ca86cc11d57324b84eb96ae7cda5c90011091/cpp/open3d/visualization/visualizer/ViewControl.cpp#L153) The output is : ``` camera_params intrinsic_matrix BEFORE: [[3605.15789 0. 947.328452]...

> The source code seems to go much deeper than that 😨 > > In the meantime, I found that `trimesh` and `pyrender` together serve my requirements 😄 Bingo! I...

@smart4654154 get canvas size `img_wh` as https://github.com/nerfstudio-project/viser/blob/dc1f02f436f85fcaaaa245f7f0509524e38d3891/examples/04_camera_poses.py#L41 Then, put you render_img to the background_img ```python def _viewer_render_fn(self, camera_state, img_wh): background_img = np.zeros((img_wh[1], img_wh[0], 3), dtype=np.uint8) if render_img is not None:...

@smart4654154 I use nerfview https://github.com/hangg7/nerfview `img_wh` set to actual size by `{client.camera.image_width}x{client.camera.image_height}` and ```python def render_fn( camera_state: nerfview.CameraState, img_wh: Tuple[int, int] ) -> np.ndarray: # Parse camera state for camera-to-world...

@smart4654154 sorry, this is the final code. I put rst to the middle of img. using the latest main branch ```python def _viewer_render_fn(self, camera_state, img_wh): img = np.zeros((img_wh[1], img_wh[0], 3),...

https://github.com/nerfstudio-project/gsplat/blob/0b4dddf04cb687367602c01196913cde6a743d70/gsplat/rendering.py#L536 In all_to_all_tensor_list https://github.com/nerfstudio-project/gsplat/blob/0b4dddf04cb687367602c01196913cde6a743d70/gsplat/distributed.py#L243-L245 means2d.grad can be attained after loss.backward() since distF.all_to_all support grad all_to_all. However not means2d.absgrad. We can manually all_to_all means2d.absgrad after loss.backward() The source code of _AlltoAll...