LiheYoung/Depth-Anything
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
PythonApache-2.0
Issues
- 0
CutMix implementation
#240 opened by tauzn-clock - 6
serious issues with the new V2 metric depth anything model and others included in the N models! needs immediate attention!
#204 opened by donrikk - 0
Error while calculating relative depth and absolute depth on kitti test dataset
#239 opened by rishanu98 - 2
train
#220 opened by IneedhelpRr - 1
Training metric depth problem
#210 opened by a1400214194 - 0
feature add
#238 opened by jonnytracker - 1
about how real depth and blackness level are related
#232 opened by srttt - 1
- 1
- 1
Encoder settings during training
#235 opened by YOUNY3 - 0
evaluate.py issue
#237 opened by Thundermean-sky - 0
3d point could
#236 opened by sctrueew - 2
- 1
@hoangtnm Only the metric model's (model finetuned on kitti dataset) output is metric, meaning in meters. The other models output relative disparity (inverse depth) upto an unknown scale and unknown shift which needs to be computed using GT for example
#233 opened by ysz-leo - 2
Selection of images in the gallery
#230 opened by NikolasE - 3
small and base weights for metric depth
#227 opened by shawnricecake - 1
Lfeat 损失没找到
#223 opened by zsw1456419654 - 5
- 3
Raw image wrong
#229 opened by jibinghu - 4
Sparse Prior
#190 opened by h1063135843 - 1
Feature alignment loss
#224 opened by schatto02 - 2
- 0
Getting issue with (indoor)
#225 opened by chnisar515 - 17
Depth Anything V2
#191 opened by emanuelevivoli - 0
Infer relative depth
#222 opened by YacineDeghaies - 0
How can calculate the actual depth value from the metric depth output of Depth Anything V2 ? What steps and conversions are necessary to obtain a precise and accurate depth calculation from the raw metric depth data(Depth Anything V2 output)?
#221 opened by padmakshmcw - 3
Custom dataset training
#216 opened by swing2331 - 1
mmseg::model registry error
#219 opened by Bion7232 - 0
How to ensure that the range of depth information obtained by the two different methods is consistent?
#218 opened by Yunnnnqiiiii - 0
- 2
TypeError: "__init__()"miss 1 requirement positional argument:"config"
#211 opened by guoyanzhongwgfufg - 1
Want more detaile about training time and GPUs!
#214 opened by YingxuanW - 1
- 3
- 0
What is the difference between Depth-Anything and control_v11f1p_sd15_depth_fp16.safetensors?
#212 opened by runshouse - 1
Metric Depth Estimation model training
#207 opened by swing2331 - 0
- 0
- 5
Batch Inference
#199 opened by maurovitaleBH - 2
ControlNet result very bad.
#203 opened by ShenZheng2000 - 2
Not detecting foreground elements
#201 opened by eyeEmotion - 0
Model Paths for controlnet experiments
#202 opened by ShenZheng2000 - 1
No progressbar/estimation time?
#200 opened by eyeEmotion - 2
- 2
OOM for Semantic Segmentation Finetuning
#197 opened by ShenZheng2000 - 1
Depth-Anything-v2 TensorRT
#193 opened by spacewalk01 - 4
BDD100K: 8M Images?
#194 opened by ShenZheng2000 - 0
Metric Depth Import Issues?
#196 opened by connorrich - 2
High idle CPU usage
#195 opened by jonahclarsen - 1
Color Map for Depth-Anything V2
#192 opened by ShenZheng2000