TRI-ML / packnet-sfm

TRI-ML Monocular Depth Estimation Repository

https://tri-ml.github.io/packnet-sfm/

TRI-ML/packnet-sfm Issues

Semantically-Guided Representation Learning for Self-Supervised Monocular Depth
Closed 2 years ago2
When will you release the code of 'Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances' (Co RL2020)
Updated 9 months ago
About input depth map and gt depth map
Updated a year ago5
About dgp : get_datum_index_for_datum_name
Closed 3 years ago6
How to calculate our own ray surface template?
Closed a year ago6
rtx 4090 RuntimeError: CUDA out of memory. How many memory is needed
Closed a year ago
Question about Equation(4) in Full surround monodepth paper
Updated a year ago
Question about paper：Learning Optical Flow, Depth, and Scene Flow Without Real-World Labels
Updated a year ago1
Details on Inv Depth Layer and ConstantPad2D
Updated a year ago
When do you plan to release the code for Full Surround Monodepth from Multiple Cameras?
Updated a year ago5
is:issue is:open How do I view the loss curve and why there is no loss output？thanks.
Updated a year ago
is:issue is:open ValueError: not enough values to unpack (expected 4, got 3) 测试kitti_tinny数据集出现这个错误是为什么
Updated a year ago1
Issue with Validation depth data processing
Updated a year ago
Error while training on custom data using Image dataset input loading
Updated 2 years ago
Is horizontal flip augmentation designed for the evaluation depth_pp_gt mode?
Closed 2 years ago1
KITTI scale-aware model
Updated 2 years ago
When estimating depth maps, RGB images and 3-channel grayscale images, which is more conducive to predicting accurate depth maps as input# Update
Updated 2 years ago
Cannot `make docker-build`
Closed 2 years ago2
PackNet-SfM model on KITTI odom split
Updated 2 years ago
About Figure 1 in FSM paper
Closed 2 years ago1
ResNet18 results with velocity supervision
Updated 2 years ago
set image_shape in infer.py
Updated 2 years ago1
Failed to reproduce the results in the paper on KITTI
Updated 2 years ago3
About the paper: Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances
Updated 2 years ago
Mixed precision training
Updated 2 years ago
Custom data set training
Closed 2 years ago2
BUG: SemiSupCompletionModel do not flip back the output['inv_depths_rgbd']
Updated 2 years ago1
Semi-Supervised Training with multiple datasets
Updated 2 years ago
About the evaluation for Full Surround Monodepth from Multiple Cameras
Updated 2 years ago7
Adding a distance bar in meter
Updated 2 years ago
`make docker-build` failed because of get-pip Python 3.6 unsupport and apex build failure
Updated 2 years ago3
Questions about using DDAD_tiny dataset.
Closed 2 years ago1
Can we use packnetmodel with mp4, video file and get result ?
Closed 2 years ago
About the Equation 5 for Full Surround Monodepth from Multiple Cameras
Updated 2 years ago20
Training schedule of PackNetSAN
Updated 2 years ago
Velocity Supervision Loss
Updated 2 years ago1
About reconstruct the fisheye point cloud
Updated 2 years ago2
3D reconstruction from multiple images - scale mismatch in depth and pose
Updated 2 years ago5
Can we create own datasets without camera calibration with only one depth camera
Updated 2 years ago2
The question for kitti dataset
Updated 2 years ago2
build 3d map from multi depth images(infer outputs)
Updated 2 years ago2
The input and gt depth visulization.
Updated 2 years ago2
About difference between PackNetSlim01.py and PackNetSAN01.py in packnet sub-module
Updated 2 years ago2
Metric scale for monocular image
Updated 3 years ago2
Full Surround Monodepth from Multiple Cameras, I have some questions about this paper，Thank you for your answer！
Updated 3 years ago3
point cloud from NRS pretrained model
Updated 3 years ago
CamViz released!
Updated 3 years ago
Better metrics with worse visual results?
Closed 3 years ago6
When train on multi-gpu，encounter ‘Read -1, expected 6144, errno = 1’
Updated 3 years ago
Loading PackNetSAN, Supervised (densified GT) pretrained model fails
Updated 3 years ago1