TRI-ML/packnet-sfm

Issues

• 3D reconstruction from multiple images - scale mismatch in depth and pose

  #213 opened 3 years ago by alexander-born
  6

• Semantically-Guided Representation Learning for Self-Supervised Monocular Depth

  #222 opened 3 years ago by fanrz
  2

• When will you release the code of 'Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances' (Co RL2020)

  #252 opened a year ago by JiaoPanpan
  0

• About input depth map and gt depth map

  #201 opened 3 years ago by mzy97
  5

• About dgp : get_datum_index_for_datum_name

  #207 opened 3 years ago by haoweiz23
  6

• How to calculate our own ray surface template?

  #249 opened 2 years ago by 942411526
  6

• rtx 4090 RuntimeError: CUDA out of memory. How many memory is needed

  #250 opened 2 years ago by 942411526
  0

• Question about Equation(4) in Full surround monodepth paper

  #248 opened 2 years ago by Hubert3123
  0

• Question about paper：Learning Optical Flow, Depth, and Scene Flow Without Real-World Labels

  #233 opened 3 years ago by longyangqi
  1

• Details on Inv Depth Layer and ConstantPad2D

  #247 opened 2 years ago by F-Barto
  0

• When do you plan to release the code for Full Surround Monodepth from Multiple Cameras?

  #202 opened 3 years ago by XiandaGuo
  5

• is:issue is:open How do I view the loss curve and why there is no loss output？thanks.

  #246 opened 2 years ago by WangGangQiang123
  0

• 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

  #245 opened 2 years ago by WangGangQiang123
  1

• Issue with Validation depth data processing

  #244 opened 2 years ago by KoushikSamudrala
  0

• Error while training on custom data using Image dataset input loading

  #243 opened 2 years ago by KoushikSamudrala
  0

• Is horizontal flip augmentation designed for the evaluation depth_pp_gt mode?

  #240 opened 2 years ago by tasizhousong
  1

• KITTI scale-aware model

  #242 opened 2 years ago by issamouawad
  0

• When estimating depth maps, RGB images and 3-channel grayscale images, which is more conducive to predicting accurate depth maps as input# Update

  #241 opened 2 years ago by hutingz
  0

• Cannot `make docker-build`

  #237 opened 2 years ago by JinraeKim
  2

• PackNet-SfM model on KITTI odom split

  #236 opened 2 years ago by hemangchawla
  0

• About Figure 1 in FSM paper

  #229 opened 2 years ago by haoweiz23
  1

• ResNet18 results with velocity supervision

  #235 opened 2 years ago by zshn25
  0

• set image_shape in infer.py

  #205 opened 3 years ago by luda1013
  1

• Failed to reproduce the results in the paper on KITTI

  #230 opened 3 years ago by Tord-Zhang
  3

• About the paper: Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances

  #232 opened 3 years ago by bizheyandebing
  0

• Mixed precision training

  #231 opened 3 years ago by hemangchawla
  0

• Custom data set training

  #223 opened 3 years ago by luda1013
  2

• BUG: SemiSupCompletionModel do not flip back the output['inv_depths_rgbd']

  #227 opened 3 years ago by chenjx1005
  1

• Semi-Supervised Training with multiple datasets

  #226 opened 3 years ago by mitalbert
  0

• About the evaluation for Full Surround Monodepth from Multiple Cameras

  #210 opened 3 years ago by weiyithu
  7

• Adding a distance bar in meter

  #225 opened 3 years ago by luda1013
  0

• `make docker-build` failed because of get-pip Python 3.6 unsupport and apex build failure

  #216 opened 3 years ago by y-okumura-isp
  3

• Questions about using DDAD_tiny dataset.

  #220 opened 3 years ago by jikerWRN
  1

• Can we use packnetmodel with mp4, video file and get result ?

  #219 opened 3 years ago by pection
  0

• About the Equation 5 for Full Surround Monodepth from Multiple Cameras

  #218 opened 3 years ago by haoweiz23
  20

• Training schedule of PackNetSAN

  #221 opened 3 years ago by jhan15
  0

• Velocity Supervision Loss

  #215 opened 3 years ago by Adamqu199541
  1

• About reconstruct the fisheye point cloud

  #212 opened 3 years ago by Oliviaaa99
  2

• Can we create own datasets without camera calibration with only one depth camera

  #214 opened 3 years ago by pection
  2

• The question for kitti dataset

  #211 opened 3 years ago by Youyi7
  2

• build 3d map from multi depth images(infer outputs)

  #209 opened 3 years ago by sparkfax
  2

• The input and gt depth visulization.

  #208 opened 3 years ago by haoweiz23
  2

• About difference between PackNetSlim01.py and PackNetSAN01.py in packnet sub-module

  #203 opened 3 years ago by mzy97
  2

• Metric scale for monocular image

  #206 opened 3 years ago by chapa17
  2

• Full Surround Monodepth from Multiple Cameras, I have some questions about this paper，Thank you for your answer！

  #204 opened 3 years ago by abing222
  3

• point cloud from NRS pretrained model

  #200 opened 3 years ago by Alvin0629
  0

• CamViz released!

  #199 opened 3 years ago by VitorGuizilini-TRI
  0

• Better metrics with worse visual results?

  #197 opened 3 years ago by jiaqixuac
  6

• When train on multi-gpu，encounter ‘Read -1, expected 6144, errno = 1’

  #198 opened 3 years ago by angiend
  0

• Loading PackNetSAN, Supervised (densified GT) pretrained model fails

  #196 opened 3 years ago by wbkit
  1