Postshot User Guide

Training Configuration


Image Selection

Use Best Images: Postshot will select sharp images that are well distributed across the scene for camera tracking and radiance field training. This is a good default to use if you don't want to pre-select images from your capture shot.

Use All Images: All imported images will be used for tracking and training. This setting may cause inferior results to Use Best Images for example if there are blurry images in the import. Using this setting is recommended only if the image sequence has been pre-selected outside of Postshot.

Max Image Count

When using the Use Best Images setting above, the Max Image Count value specifies how many images will be selected from the imported image sequence. Typical values range between 100 and 300.

Image counts below 100 are still possible, but most reasonable results require about 100 or more images.

On the other hand, using many more images won't hurt the quality (assuming all images are sharp and well trackable), but they may not improve it either. Using images that were taken from very similar view points won't give the radiance field enough additional information about the scene to justify the processing time.

Max Image Size

Postshot will reduce the image size such that the larger dimension is no larger that the Max Image Size value. Very high resolutions like the 4-8k images DSLMs produce, may be overkill for radiance field training at the moment.

Splat training is faster the smaller the images are. NeRF training will seem to run equally fast, but it will take longer until the radiance field has 'seen' the entire scene.

We thus recommend sticking to the default or even lowering it for faster training unless you are specifically experimenting with high resolutions.

Camera Poses

When import images or video, Postshot will compute the camera poses from the images - a process also called Camera Tracking. This is a multi-step process and will take some time before the radiance field training can begin.

If you have already tracked your shot with tools, you can also import the camera poses. To do this, simply drop both the images and the camera pose database into Postshot.

Max Features/Frame

This value controls the maximum number of feature points that will be extracted for one frame during Camera Tracking. The more features are extracted, the more 3D points will be generated. This can help improve the accuracy of the camera poses and when using the Splat profile also the quality of the radiance field.

However, higher numbers may cause the tracking process to take longer. Low numbers, like 4 kFeatures or less, may cause the tracking to fail.

Radiance Field Profile

Postshot supports two different models to create radiance fields: Gaussian Splatting (Splat) and Neural Radiance Fields (NeRF).

When using the Splat profile, the 3D points created during camera tracking will be turned into 'splats' to reconstruct the scene. The training process will then keep adding more points to increase the accuracy of the reconstruction.

The Splat profile allows for very fast rendering and quickly reconstructs fine detail in well-covered regions of the scene. In the current development stage, the downside is that that the reconstruction artefacts are arguably more salient than those of the NeRF models.

When using the NeRF model, the maximum accuracy has to be specified before the training can begin. Postshot currently provides five sizes (S, M, L, XL, XXL) for NeRF models.

In the current development stage, NeRFs are slower to render than Splats, but tend to generalize better. That is, the images may hold up better when moving farther away from the original camera positions.

Here is an intuition for how 'large' the NeRF profile options are:

S is for toy-like testing.

M is a significant step up, such that real scenes can be reasonably captured with low memory requirements.

L is the recommended default if you want to produce good image quality.

XL and XXL are for pushing toward fine detail in the scene center or for large scenes.

Splat Density (only in Splat profile)

When using the Splat profile, this value controls how sensitively the model reacts to inaccuracies by creating new splats. Values larger than 1.0 cause it to be more sensitive, creating splats already for smaller inaccuracies. This results in more splats to be generated during training. Values less than 1.0 make it less sensitive, causing fewer splats to be generated.

If there is not enough detail in your splat model, you can try increasing this value. You can change this value during training or continue training with a different value after it has been paused.

Sampling Mode (only in NeRF profiles)

After the NeRF model size, the Sampling Mode is the next important settings that affects the quality of the radiance field. The options differ in quality and compute cost:

Fast produces the lowest quality, which usually means blurrier images. But it is the fastest.

Focused clusters samples close to surfaces in the scene, thereby allowing for improved definition.

Multisampled further improves reconstruction of fine and/or distant structures at an increased compute cost.

Refine Camera Poses (only in NeRF profiles)

The camera poses create by the Camera Tracking process can be of varying accuracy. Especially if they have been generated by real-time tracking methods and then been imported into Postshot.

If the camera poses have low accuracy, the radiance field quality will suffer significantly. If this option is enabled, Postshot will improve the accuracy of the camera poses while training the radiance field. This can save a shot entirely if the poses were poor. On the other hand, if the shot was tracked well, it may not improve anything. In this case it will be somewhat faster to train without pose refinement.

Start Training

Leave this box checked to automatically start tracking and training after importing the images.

Stop Training After

If checked, Postshot will stop training after the specified number of steps. 30 kSteps is a good starting point for many scenes. When using NeRF L or larger models and pushing for fine detail or large scenes, more than 30 kSteps will likely be necessary. While most of the convergence occurs during early training steps, there can still be significant improvements in image quality after twice that amount or more.