Camera pose optimization for Splatfacto #2891

oseiskar · 2024-02-09T17:59:01Z

Updated description, April 7: Camera pose optimization for Splatfacto, based on nerfstudio-project/gsplat#127, which is included in gsplat 0.1.9+. See #2891 (comment) for instructions and examples.

.
Original description, outdated: ~~This PR is intended as an extension of #2885, but I could not easily create a PR to that branch, so creating a new PR instead. A detailed description in a comment in the original PR: #2885 (comment)~~
~~@jh-surh : Feel free to merge / cherry-pick any of my commits in this branch to your original PR, [...]~~

ichsan2895 · 2024-02-09T23:34:37Z

Again, interesting PR. 👍
How about the result quality? Hopefully it increase the quality when using colmap.

Is it compatible with latest gsplat==0.1.5 ? or we need git install from this repo nerfstudio-project/gsplat#127 ?

ichsan2895 · 2024-02-10T04:47:54Z

Sorry, Unfortunatelly, it decrease the quality:

`Playroom` dataset processed by `colmap 3.8`: (Red line = this PR)

Camera optimization regularizer acts after 3k iters, then the PSNR begins to drop.

`desolation` dataset provided by `ns-download-data`: (Red line = this PR)

Camera optimization regularizer acts after 3k iters, then the PSNR begins to drop.

oseiskar · 2024-02-10T08:06:34Z

Sorry, Unfortunatelly, it decrease the quality:

This is expected. Like I commented here #2885 (comment), there are two separate cases:

The current NeRF/3DGS benchmark datasets which are still images taken on a tripod. For these, COLMAP works very accurately and there's no need to further optimize the poses. If pose optimization is enabled it easily decreases quality. It might be possible to tune the hyperparameters so that this would not happen, but I have not attempted that
Datasets collected with a moving mobile camera, similar to the one @jh-surh was testing with in the other PR. The goal of this PR is to improve these cases, especially in scenarios, where COLMAP has been replaced with a faster alternative like ARKit's online poses or other systems. The issue is that there is no good standard benchmark set for these at the moment (as far as I know)

I now disabled the feature by default so that the assumed target use case remains as 1. (2. can be addressed by re-enabling this on the command line as --pipeline.model.camera-optimizer.mode=SO3xR3)

Again, interesting PR. 👍 How about the result quality? Hopefully it increase the quality when using colmap.

Is it compatible with latest gsplat==0.1.5 ? or we need git install from this repo nerfstudio-project/gsplat#127 ?

No. Need to install from Git since the view matrix gradients from nerfstudio-project/gsplat#127 (or, alternatively, nerfstudio-project/gsplat#123) are neeed.

ichsan2895 · 2024-02-10T08:39:58Z

Sorry, Unfortunatelly, it decrease the quality:

This is expected. Like I commented here #2885 (comment), there are two separate cases:
1. The current NeRF/3DGS benchmark datasets which are still images taken on a tripod. For these COLMAP works very accurately and there's no need to further optimize the poses. If pose optimization is enabled it easily decreases quality. It might be possible to tune the hyperparameters so that this would not happen, but I have not attempted that

2. Datasets collected with a moving mobile camera, similar to the one @jh-surh was testing with in the [other PR](https://github.com/nerfstudio-project/nerfstudio/pull/2885). The goal of this PR is to improve these cases, especially in scenarios, where COLMAP has been replaced with a faster alternative like ARKit's online poses or other systems. The issue is that there is no good standard benchmark set for these at the moment (as far as I know)
I now disabled the feature by default so that the assumed target use case remains as 1. (2. can be addressed by re-enabling this on the command line as --pipeline.model.camera-optimizer.mode=SO3xR3)

Again, interesting PR. 👍 How about the result quality? Hopefully it increase the quality when using colmap.
Is it compatible with latest gsplat==0.1.5 ? or we need git install from this repo nerfstudio-project/gsplat#127 ?

No. Need to install from Git since the view matrix gradients from nerfstudio-project/gsplat#127 (or, alternatively, nerfstudio-project/gsplat#123) are neeed.

Thanks for your clarification, in my experiment before, I already use gsplat from this source:

git clone --branch approximate-viewmat-gradient https://github.com/SpectacularAI/gsplat
git submodule update --init --recursive

I think it is good if the camera opt can detect automatically if the poses already accurate or not. If it already accurate and it hurts quality, it will be turn off.

But I am sorry I can not coding since it too advance for me.

kerrj · 2024-02-12T22:27:31Z

I think these changes look reasonable to me, delaying pose optimization until partial convergence makes sense. @jh-surh have you had a chance to take a look?

jb-ye · 2024-02-13T22:24:48Z

Regarding quantitative validation of this PR, Here is my suggestion:

(1) take a dataset which you think is suitable for pose optimization
(2) run a baseline with pose optimization disabled and obtain PSNR metrics on validation images.
(3a) run with pose optimization enabled for all frames (basically all images are used for training) and extract the optimized poses
(3b) use the optimized poses to re-run the same setting as done in (2) and compare the PSNR metrics on validation images.

If (3b) is better than (2), one has strong evidence that pose optimization works.

What do you think? @oseiskar

jb-ye · 2024-02-13T22:35:25Z

I think these changes look reasonable to me, delaying pose optimization until partial convergence makes sense. @jh-surh have you had a chance to take a look?

Delay pose optimization until partial convergence might be useful for fixing a few bad local poses, but would not correct systematic drift in SfM/SLAM.

oseiskar · 2024-02-14T07:29:46Z

Regarding quantitative validation of this PR, Here is my suggestion:

(1) take a dataset which you think is suitable for pose optimization (2) run a baseline with pose optimization disabled and obtain PSNR metrics on validation images. (3a) run with pose optimization enabled for all frames (basically all images are used for training) and extract the optimized poses (3b) use the optimized poses to re-run the same setting as done in (2) and compare the PSNR metrics on validation images.

If (3b) is better than (2), one has strong evidence that pose optimization works.

What do you think? @oseiskar

I think this makes a lot of sense. I am planning to do that in the near-ish future.

To clarify, this PR is not yet in the state where it would be robust enough for general use. The main intention was to help #2885 so that it's not necessary to reinvent the wheel in all aspects there. In particular, I think if this commit 5fe47c9 is probably a pre-requisite for getting anything working well. These new metrics 3b02a7f can also be helpful for debugging/monitoring pose optimization.

jh-surh · 2024-02-14T15:41:49Z

I think these changes look reasonable to me, delaying pose optimization until partial convergence makes sense. @jh-surh have you had a chance to take a look?

I think the changes look good. I'll try them out.

Regarding quantitative validation of this PR, Here is my suggestion:

(1) take a dataset which you think is suitable for pose optimization (2) run a baseline with pose optimization disabled and obtain PSNR metrics on validation images. (3a) run with pose optimization enabled for all frames (basically all images are used for training) and extract the optimized poses (3b) use the optimized poses to re-run the same setting as done in (2) and compare the PSNR metrics on validation images.

If (3b) is better than (2), one has strong evidence that pose optimization works.

What do you think? @oseiskar

Wouldn't (3a) showing a better PSNR already show that the pose optimization works?

jb-ye · 2024-02-14T17:40:05Z

Wouldn't (3a) showing a better PSNR already show that the pose optimization works?

(3a) uses all images to train, so the metrics calculated on the set of validation images is biased. Evaluation on hold out set of images for calculating metrics like (3b) is unbiased and produce apple-to-apple comparison to (2).

In (3b), image data of validation sets are only used to optimize their poses, but not gaussian splat models.

MartinEthier · 2024-02-16T18:24:34Z

Regarding quantitative validation of this PR, Here is my suggestion:

(1) take a dataset which you think is suitable for pose optimization (2) run a baseline with pose optimization disabled and obtain PSNR metrics on validation images. (3a) run with pose optimization enabled for all frames (basically all images are used for training) and extract the optimized poses (3b) use the optimized poses to re-run the same setting as done in (2) and compare the PSNR metrics on validation images.

If (3b) is better than (2), one has strong evidence that pose optimization works.

What do you think? @oseiskar

I've been looking into ways to enable evaluation using pose optimization and I tried the method you outlined using nerfacto and nerfacto-big. For some reason, my results on the extracted optimized poses are worse than simply not using pose optimization, even though the training PSNR increases when I enable pose optimization, indicating that it helps. See my comment here for more details: #2863 (comment). Do you have any ideas why this might be the case?

oseiskar · 2024-04-06T09:17:13Z

@ichsan2895 @jb-ye I now rebased this on top of the current main branch (with #3019), removed deprecated workarounds and changed the hyperparameters to what we used in Gaussian Splatting on the Move.

Here's how to test branch and verify that it works: First, install and download a suitable test dataset (our version of Deblur-NeRF, which contains a variant with artificial pose noise):

conda activate nerfstudio

# download a suitable dataset
git clone https://github.com/SpectacularAI/3dgs-deblur
cd 3dgs-deblur
python download_data.py --dataset synthetic
cd ..

# check out and install this branch
https://github.com/SpectacularAI/nerfstudio
cd nerfstudio
git checkout camera-pose-optimization
pip install -e .

Then, run a basline test with the noisy pose data but without pose optimization:

ns-train splatfacto --data ../3dgs-deblur/data/inputs-processed/synthetic-posenoise/cozyroom

Then check Viser: Looks terrible (Figure 1). Now, let's run another test with pose optimization:

ns-train splatfacto --data ../3dgs-deblur/data/inputs-processed/synthetic-posenoise/cozyroom \
    --pipeline.model.camera-optimizer.mode=SO3xR3

Check viser again: Looks great (Figure 2). (Bonus: also add --pipeline.model.rasterize-mode=antialiased for best results)

Now, the caveats:

Evaluating this numerically is not trivial, for the following reasons:
a) We would also need to optimize the evaluation image poses or most of the error in, e.g., PSNR is caused by just "misaligned" evaluation images. This topic is also discussed by @LingzheZhao here.
b) Even if we do, cases with very well-optimized poses probably degrade (this concrens of most academic benchmark data out there, which is mostly consists of still images taken on tripods, or synthetics). This is because we waste some iterations that could be spent refining the 3D model into refining the poses, especially early in the optimization and during this time, when camera poses can move a lot, the 3D model remains blurrier than without pose opt. This can be solved with a 2-pass approach, which we also used in the paper.
c) If evaluation images are used during training, even in the first pass, one could argue that they improve the model and the results are overly optimistic. To avoid this, the two-pass optimization should actually work like this: 1st pass: train normally without evaluation images, 2nd pass: optimize evaluation image poses with fixed Gaussian parameters. I have not tried to implement this since I think it's really a bit overkill in this context.
The pose optimization can fail depending on the scene. This is sensitive to the following parameters: pipeline.model.camera-optimizer.trans-l2-penalty and auto-scale-poses (dataparser), which is relevant if the dataset has absolute metric scale (e.g., from VISLAM). It should be possible to improve this in the future with more carefully designed priors, e.g., penalizing maxium deviation from the initial poses more strongly.

In any case, I think this PR is now in a mergeable state despite the (minor) weaknesses above. The pose optimization is now anyway off by default.

Figure 1: Baseline

Figure 2: With pose optimization

This was actually with --pipeline.model.rasterize-mode=antialiased. Here's how it looks with the default rasterization. Still better than with noisy poses, but the new rasterization gives a nice super-resolution capability here (training data is 600x400)

jb-ye · 2024-04-08T15:13:54Z

@oseiskar Thanks, I will try to take a closer look in the next few days.

jb-ye

Looks good to me, some minor comments.

jb-ye · 2024-04-09T20:11:21Z

nerfstudio/configs/method_configs.py

@@ -632,8 +632,10 @@
        },
        "quats": {"optimizer": AdamOptimizerConfig(lr=0.001, eps=1e-15), "scheduler": None},
        "camera_opt": {
-            "optimizer": AdamOptimizerConfig(lr=1e-3, eps=1e-15),
-            "scheduler": ExponentialDecaySchedulerConfig(lr_final=5e-5, max_steps=30000),
+            "optimizer": AdamOptimizerConfig(lr=1e-4, eps=1e-15),


Could you add this change to "splatfacto-big" config?

ichsan2895 · 2024-04-10T15:01:47Z

Hello, interesting PR to be implemented.

Here is my own dataset (already processed with colmap) with some of motion blur. Already processed by colmap & colmap image_undistorter Feel free for testing it.

Lubuk_torok_scenery

oseiskar · 2024-04-10T16:47:10Z

@jb-ye : Done. I tested very briefly (i.e., only with this same synthetic scene) that it looks reasonable and better than the old splatfacto-big camera pose opt. defaults. This was the case (result here) so these are probably a good starting point for further hyperparameter tuning.

@ichsan2895 To clarify, this PR does not implement motion blur compensation. This is just one of the building blocks that can help in that goal and other tasks as well. For testing the Gaussian Splatting on the Move method with custom data, see here.

lxzbg · 2024-04-11T04:00:26Z

@oseiskar Great work. I used ARkit's pose based data for testing, and it did work.
However, I have some observations.

When the pose error is small, it can be corrected very well;
When the pose error is large, it cannot be completely corrected (I tried adjusting the number of iterations, learning rate, and warnup, but this only had a little effect);
The pose optimization is more accurate in the inner area of the surround shot, but in the surrounding area, it seems that pose optimization is not that effective (maybe this observation is incorrect).

Is there anything that can be improved here?

oseiskar · 2024-04-11T06:38:58Z

@lxzbg Thank you for testing, good to hear that this also gave positive results in your test. I think those observations all make sense. In general, there is a lot that can be improved around this topic, but probably not in the scope of this PR.

Getting 3DGS to work robustly for data with larger pose errors probably requires a combination of different techniques, where 3DGS pose optimization like this is one piece in the puzzle. Replacing COLMAP with some of the new methods like Dust3r or Cameras as Rays seems like a promising direction. This was already verified to work well by the InstantSplat authors.

It is probably also possible to improve performance a bit by further tuning of these hyperparameters, but I would not expect miracles there. I am not planning to try further performance improvements in this PR.

jb-ye

thanks for the effort!

jb-ye · 2024-04-11T17:13:55Z

@oseiskar You need to rebase and the PR should be auto-merged.

Do not chain modifications to camera_to_worlds to improve numerical stability and enable L2 rot/trans penalties.

Parameters used in the Gaussian Splatting on the Move paper v1

Same parameters as in normal Splatfacto

oseiskar · 2024-04-11T18:21:23Z

@jb-ye Great! I now rebased but auto-merge seems to have been auto-disabled

commit d9b022b Author: J.Y <[email protected]> Date: Fri Apr 19 14:03:55 2024 -0400 Allow alpha transparency training for blender datasets input (nerfstudio-project#3088) Allow alpha transparency training for rgba input Co-authored-by: Justin Kerr <[email protected]> commit eddf2d2 Author: Congrong Xu <[email protected]> Date: Thu Apr 18 17:37:50 2024 -0700 Changes for trainer.py to support the Gradio webui (nerfstudio-project#3046) * changes for trainer to support webui * Update trainer to support webui * format * add a seperated shutdown() function to stop training * typo fix * get rid of _stop_viewer_server() * Update trainer.py * organize import --------- Co-authored-by: Brent Yi <[email protected]> commit 45d8bb7 Author: Justin Kerr <[email protected]> Date: Wed Apr 17 23:54:43 2024 -0700 updates to apply_pca_colormap (nerfstudio-project#3086) * improvements to pca_colormap: allow input pca matrix, optional ignore_zeros arg * typo commit babf577 Author: Patrick Morgan <[email protected]> Date: Fri Apr 12 14:23:47 2024 -0700 Fix call to detect ODM reconstruction file (nerfstudio-project#3018) commit a64026f Author: Justin Kerr <[email protected]> Date: Fri Apr 12 12:32:22 2024 -0700 shift principle points by .5 in undistortion (nerfstudio-project#3071) * shift principle points by .5 * fix ordering * add fisheye offset commit c302cc5 Author: Gunjan Chhablani <[email protected]> Date: Thu Apr 11 16:41:14 2024 -0400 Add pointcloud loading for blender parser (nerfstudio-project#2902) * Add pointcloud loading for blender parser * Fix argument * Fix docstring * Fix metadata in dataparsers * Add changes from review * Avoid changing default behavior * Apply `scale_factor` to loaded points --------- Co-authored-by: Brent Yi <[email protected]> commit 03bdeff Author: hyperzy <[email protected]> Date: Thu Apr 11 14:56:37 2024 -0400 Fixed Unexpectedly huge RAM consumption of parallel datamanager (nerfstudio-project#3060) * Reduced the memory usage by caching image after the datamanager process starts commit 4714ae7 Author: J.Y <[email protected]> Date: Thu Apr 11 14:37:02 2024 -0400 write eval combined images for diagnostics (nerfstudio-project#3070) commit eba72db Author: Otto Seiskari <[email protected]> Date: Thu Apr 11 21:23:17 2024 +0300 Camera pose optimization for Splatfacto (nerfstudio-project#2891) * Add pose optimization to Splatfacto * Disable Splatfacto pose optimization by default * Improve apply_to_camera for Gaussian Splatting pose optimization Do not chain modifications to camera_to_worlds to improve numerical stability and enable L2 rot/trans penalties. * Add separate mean and max rot/trans metrics to camera-opt * Tweak pose optimization hyperparameters Parameters used in the Gaussian Splatting on the Move paper v1 * Unit test fix for new cameara_optimizer training metrics * Adjust splatfacto-big camera pose optimization parameters Same parameters as in normal Splatfacto --------- Co-authored-by: jh-surh <[email protected]> commit 2d9bbe5 Author: dberga <[email protected]> Date: Thu Apr 11 04:04:33 2024 +0200 fix exporter.py for FullImageDataManager and RandomCamerasDataManager (nerfstudio-project#3065) * fix exporter.py for FullImageDataManager and RandomCamerasDataManager * sort imports * ruff --------- Co-authored-by: Brent Yi <[email protected]> commit c381fc8 Author: Justin Kerr <[email protected]> Date: Wed Apr 10 18:59:20 2024 -0700 Fix custom elements nested under @Property (nerfstudio-project#3066) * patch custom elements bug * Skip `cached_property` * fomrat * comment, type hint --------- Co-authored-by: Brent Yi <[email protected]> commit d1fc2ee Author: Saurav Maheshkar <[email protected]> Date: Mon Apr 8 23:46:00 2024 +0100 feat(ci): migrate to `uv` in CI (nerfstudio-project#3038) * feat(ci): migrate to `uv` in CI * feat(ci): drop upgrade strategy * feat(ci): use `uv` in docs workflow * fix(ci/doc): update sphinx build cmd * fix(ci/doc): specify python path * (experimental) simplify * remove venv * Revert line wrap change for doc.yml --------- Co-authored-by: Brent Yi <[email protected]> commit 2b91715 Author: Sahil Jain <[email protected]> Date: Mon Apr 8 13:04:20 2024 -0400 Fix config loading for Eyeful Tower dataset (nerfstudio-project#3054) Add test_filenames to transforms.json generated by eyeful_tower.py commit 26804f8 Author: Ling Jing <[email protected]> Date: Tue Apr 9 00:07:21 2024 +0800 Make colmapDataParser compatible with 360_v2 dataset format (nerfstudio-project#2860) * added an option to colmapdataparser to round up the image size when downscaling * add round mode and update ffmpeg command * [fix] wrong variable order * update format --------- Co-authored-by: Jing <[email protected]> commit 911091c Author: Jan-Niklas Dihlmann <[email protected]> Date: Mon Apr 8 16:17:56 2024 +0200 Added SIGNeRF to Nerfstudio methods (nerfstudio-project#3053) * feat: signerf as nerfstudio method * fix: formating issues and indexing

* Add pose optimization to Splatfacto * Disable Splatfacto pose optimization by default * Improve apply_to_camera for Gaussian Splatting pose optimization Do not chain modifications to camera_to_worlds to improve numerical stability and enable L2 rot/trans penalties. * Add separate mean and max rot/trans metrics to camera-opt * Tweak pose optimization hyperparameters Parameters used in the Gaussian Splatting on the Move paper v1 * Unit test fix for new cameara_optimizer training metrics * Adjust splatfacto-big camera pose optimization parameters Same parameters as in normal Splatfacto --------- Co-authored-by: jh-surh <[email protected]>

oseiskar mentioned this pull request Feb 9, 2024

Add pose optimization to Splatfacto #2885

Closed

LingzheZhao mentioned this pull request Mar 21, 2024

Eval images metrics does not show in WanDB WU-CVGL/BAD-Gaussians#3

Closed

oseiskar force-pushed the camera-pose-optimization branch from e162f0c to 1384df1 Compare April 6, 2024 08:27

oseiskar force-pushed the camera-pose-optimization branch 2 times, most recently from 730557a to 4f43b8e Compare April 6, 2024 10:08

oseiskar changed the title ~~Camera pose optimization tweaks for Splatfacto~~ Camera pose optimization for Splatfacto Apr 7, 2024

oseiskar force-pushed the camera-pose-optimization branch from 70a5ec6 to 197c3ab Compare April 7, 2024 17:05

jb-ye reviewed Apr 9, 2024

View reviewed changes

oseiskar force-pushed the camera-pose-optimization branch from 197c3ab to 4aafd50 Compare April 10, 2024 16:35

jb-ye approved these changes Apr 11, 2024

View reviewed changes

jb-ye enabled auto-merge (squash) April 11, 2024 17:13

Add pose optimization to Splatfacto

0dea70c

oseiskar added 6 commits April 11, 2024 21:05

Disable Splatfacto pose optimization by default

fb24508

Improve apply_to_camera for Gaussian Splatting pose optimization

e8e05ff

Do not chain modifications to camera_to_worlds to improve numerical stability and enable L2 rot/trans penalties.

Add separate mean and max rot/trans metrics to camera-opt

bb40745

Tweak pose optimization hyperparameters

beac3c0

Parameters used in the Gaussian Splatting on the Move paper v1

Unit test fix for new cameara_optimizer training metrics

bd33e65

Adjust splatfacto-big camera pose optimization parameters

dc62759

Same parameters as in normal Splatfacto

auto-merge was automatically disabled April 11, 2024 18:06
Head branch was pushed to by a user without write access

oseiskar force-pushed the camera-pose-optimization branch from 4aafd50 to dc62759 Compare April 11, 2024 18:06

jb-ye merged commit eba72db into nerfstudio-project:main Apr 11, 2024
2 checks passed

maturk mentioned this pull request Apr 15, 2024

how can i get transforms.json maturk/dn-splatter#8

Open

oseiskar mentioned this pull request Apr 28, 2024

Export Splatfacto-optimized poses #3116

Merged

oseiskar deleted the camera-pose-optimization branch May 30, 2024 19:53

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Camera pose optimization for Splatfacto #2891

Camera pose optimization for Splatfacto #2891

oseiskar commented Feb 9, 2024 •

edited

Loading

ichsan2895 commented Feb 9, 2024

ichsan2895 commented Feb 10, 2024 •

edited

Loading

oseiskar commented Feb 10, 2024 •

edited

Loading

ichsan2895 commented Feb 10, 2024 •

edited

Loading

kerrj commented Feb 12, 2024

jb-ye commented Feb 13, 2024 •

edited

Loading

jb-ye commented Feb 13, 2024

oseiskar commented Feb 14, 2024

jh-surh commented Feb 14, 2024

jb-ye commented Feb 14, 2024 •

edited

Loading

MartinEthier commented Feb 16, 2024

oseiskar commented Apr 6, 2024

jb-ye commented Apr 8, 2024

jb-ye left a comment

jb-ye Apr 9, 2024

ichsan2895 commented Apr 10, 2024

oseiskar commented Apr 10, 2024

lxzbg commented Apr 11, 2024 •

edited

Loading

oseiskar commented Apr 11, 2024

jb-ye left a comment

jb-ye commented Apr 11, 2024

oseiskar commented Apr 11, 2024

Camera pose optimization for Splatfacto #2891

Camera pose optimization for Splatfacto #2891

Conversation

oseiskar commented Feb 9, 2024 • edited Loading

ichsan2895 commented Feb 9, 2024

ichsan2895 commented Feb 10, 2024 • edited Loading

Playroom dataset processed by colmap 3.8: (Red line = this PR)

desolation dataset provided by ns-download-data: (Red line = this PR)

oseiskar commented Feb 10, 2024 • edited Loading

ichsan2895 commented Feb 10, 2024 • edited Loading

kerrj commented Feb 12, 2024

jb-ye commented Feb 13, 2024 • edited Loading

jb-ye commented Feb 13, 2024

oseiskar commented Feb 14, 2024

jh-surh commented Feb 14, 2024

jb-ye commented Feb 14, 2024 • edited Loading

MartinEthier commented Feb 16, 2024

oseiskar commented Apr 6, 2024

Figure 1: Baseline

Figure 2: With pose optimization

jb-ye commented Apr 8, 2024

jb-ye left a comment

Choose a reason for hiding this comment

jb-ye Apr 9, 2024

Choose a reason for hiding this comment

ichsan2895 commented Apr 10, 2024

oseiskar commented Apr 10, 2024

lxzbg commented Apr 11, 2024 • edited Loading

oseiskar commented Apr 11, 2024

jb-ye left a comment

Choose a reason for hiding this comment

jb-ye commented Apr 11, 2024

oseiskar commented Apr 11, 2024

oseiskar commented Feb 9, 2024 •

edited

Loading

ichsan2895 commented Feb 10, 2024 •

edited

Loading

`Playroom` dataset processed by `colmap 3.8`: (Red line = this PR)

`desolation` dataset provided by `ns-download-data`: (Red line = this PR)

oseiskar commented Feb 10, 2024 •

edited

Loading

ichsan2895 commented Feb 10, 2024 •

edited

Loading

jb-ye commented Feb 13, 2024 •

edited

Loading

jb-ye commented Feb 14, 2024 •

edited

Loading

lxzbg commented Apr 11, 2024 •

edited

Loading