Frame-decimated clips with their original cadence

Base Plate: Pan, City Skyline

A skyline scrolling at a constant 3.5 pixels per frame: pure horizontal translation with no rotation or scale change. The lit windows give sparse high-contrast features to track, and the constant velocity means the correct answer for interpolation and optical flow is known exactly. One of eight shared base plates: every AI-video suite in this library degrades one of these rather than inventing its own footage, so results across suites are comparable. Encoded at CRF 14 (well above the house CRF 30), because a reference compressed as hard as the material under test puts the measurement floor above the effect being measured.

File: MP4 · Base Plates · 640x360
Use case: Video stabilisationFrame interpolation+1· Conversion set

Base Plate: Depth, Three Parallax Planes

Far, mid and near layers translating at 0.6, 2.4 and 6.0 pixels per frame. Relative depth is defined by the motion ratio rather than guessed from cues, which gives depth-from-video and optical-flow output something objective to be scored against. One of eight shared base plates: every AI-video suite in this library degrades one of these rather than inventing its own footage, so results across suites are comparable. Encoded at CRF 14 (well above the house CRF 30), because a reference compressed as hard as the material under test puts the measurement floor above the effect being measured.

File: MP4 · Base Plates · 640x360
Use case: Frame interpolationVideo QA· Conversion set

Interpolation Ground Truth: pan-city at 24 fps

The full-rate 24 fps reference for the pan-city interpolation set. The decimated clips in this group drop frames from exactly this sequence, so every frame an interpolator is asked to synthesise has a true original to be scored against, which is the only way to tell invention from reconstruction.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo QA· Conversion set

Interpolation Input: pan-city at 12 fps

The pan-city plate decimated to 12 fps by keeping every 2th frame, so 24 of the original 48 frames are missing. Interpolate back to 24 fps and each synthesised frame has an exact counterpart in the ground truth. Larger gaps need genuine motion understanding rather than blending.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo QA· Conversion set

Interpolation Input: pan-city at 8 fps

The pan-city plate decimated to 8 fps by keeping every 3th frame, so 32 of the original 48 frames are missing. Interpolate back to 24 fps and each synthesised frame has an exact counterpart in the ground truth. Larger gaps need genuine motion understanding rather than blending.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo QA· Conversion set

Interpolation Input: pan-city at 6 fps

The pan-city plate decimated to 6 fps by keeping every 4th frame, so 36 of the original 48 frames are missing. Interpolate back to 24 fps and each synthesised frame has an exact counterpart in the ground truth. Larger gaps need genuine motion understanding rather than blending.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo QA· Conversion set

Interpolation Input: pan-city, Motion-Blurred Decimation

Halved frame rate where each output frame is the AVERAGE of the two it replaces, rather than one of them: what a long shutter angle actually produces. Substantially harder than clean decimation, because the interpolator must undo motion blur as well as invent the missing instants, and no input frame matches any ground-truth frame exactly.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo deblur+1· Conversion set

Interpolation Ground Truth: orbit-solid at 24 fps

The full-rate 24 fps reference for the orbit-solid interpolation set. The decimated clips in this group drop frames from exactly this sequence, so every frame an interpolator is asked to synthesise has a true original to be scored against, which is the only way to tell invention from reconstruction.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo QA· Conversion set

Interpolation Input: orbit-solid at 12 fps

The orbit-solid plate decimated to 12 fps by keeping every 2th frame, so 24 of the original 48 frames are missing. Interpolate back to 24 fps and each synthesised frame has an exact counterpart in the ground truth. Larger gaps need genuine motion understanding rather than blending.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo QA· Conversion set

Interpolation Input: orbit-solid at 8 fps

The orbit-solid plate decimated to 8 fps by keeping every 3th frame, so 32 of the original 48 frames are missing. Interpolate back to 24 fps and each synthesised frame has an exact counterpart in the ground truth. Larger gaps need genuine motion understanding rather than blending.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo QA· Conversion set

Interpolation Input: orbit-solid at 6 fps

The orbit-solid plate decimated to 6 fps by keeping every 4th frame, so 36 of the original 48 frames are missing. Interpolate back to 24 fps and each synthesised frame has an exact counterpart in the ground truth. Larger gaps need genuine motion understanding rather than blending.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo QA· Conversion set

Interpolation Input: orbit-solid, Motion-Blurred Decimation

Halved frame rate where each output frame is the AVERAGE of the two it replaces, rather than one of them: what a long shutter angle actually produces. Substantially harder than clean decimation, because the interpolator must undo motion blur as well as invent the missing instants, and no input frame matches any ground-truth frame exactly.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo deblur+1· Conversion set

Interpolation Ground Truth: depth-layers at 24 fps

The full-rate 24 fps reference for the depth-layers interpolation set. The decimated clips in this group drop frames from exactly this sequence, so every frame an interpolator is asked to synthesise has a true original to be scored against, which is the only way to tell invention from reconstruction.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo QA· Conversion set

Interpolation Input: depth-layers at 12 fps

The depth-layers plate decimated to 12 fps by keeping every 2th frame, so 24 of the original 48 frames are missing. Interpolate back to 24 fps and each synthesised frame has an exact counterpart in the ground truth. Larger gaps need genuine motion understanding rather than blending.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo QA· Conversion set

Interpolation Input: depth-layers at 8 fps

The depth-layers plate decimated to 8 fps by keeping every 3th frame, so 32 of the original 48 frames are missing. Interpolate back to 24 fps and each synthesised frame has an exact counterpart in the ground truth. Larger gaps need genuine motion understanding rather than blending.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo QA· Conversion set

Interpolation Input: depth-layers at 6 fps

The depth-layers plate decimated to 6 fps by keeping every 4th frame, so 36 of the original 48 frames are missing. Interpolate back to 24 fps and each synthesised frame has an exact counterpart in the ground truth. Larger gaps need genuine motion understanding rather than blending.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo QA· Conversion set

Interpolation Input: depth-layers, Motion-Blurred Decimation

Halved frame rate where each output frame is the AVERAGE of the two it replaces, rather than one of them: what a long shutter angle actually produces. Substantially harder than clean decimation, because the interpolator must undo motion blur as well as invent the missing instants, and no input frame matches any ground-truth frame exactly.

File: MP4 · Interp · 640x360
Use case: Frame interpolationVideo deblur+1· Conversion set

Depth Input: Three-Layer Parallax Scene

Three planes translating at 0.6, 2.4 and 6.0 pixels per frame, a 1 : 4 : 10 velocity ratio that defines their relative depth by motion alone. There are no pictorial depth cues to fall back on: no perspective convergence, no shading, no familiar object sizes. A monocular depth model that has learned pictorial cues rather than motion parallax will do poorly here, which is precisely what makes the fixture informative.

File: MP4 · Depth · 640x360
Use case: Depth from videoFrame interpolation+1· Conversion set