Inter frame | EPFL Graph Search

An inter frame is a frame in a video compression stream which is expressed in terms of one or more neighboring frames. The "inter" part of the term refers to the use of Inter frame prediction. This kind of prediction tries to take advantage from temporal redundancy between neighboring frames enabling higher compression rates. An inter coded frame is divided into blocks known as macroblocks. After that, instead of directly encoding the raw pixel values for each block, the encoder will try to find a block similar to the one it is encoding on a previously encoded frame, referred to as a reference frame. This process is done by a block matching algorithm. If the encoder succeeds on its search, the block could be encoded by a vector, known as motion vector, which points to the position of the matching block at the reference frame. The process of motion vector determination is called motion estimation. In most cases the encoder will succeed, but the block found is likely not an exact match to the block it is encoding. This is why the encoder will compute the differences between them. Those residual values are known as the prediction error and need to be transformed and sent to the decoder. To sum up, if the encoder succeeds in finding a matching block on a reference frame, it will obtain a motion vector pointing to the matched block and a prediction error. Using both elements, the decoder will be able to recover the raw pixels of the block. The following image shows the whole process graphically: This kind of prediction has some pros and cons: If everything goes fine, the algorithm will be able to find a matching block with little prediction error so that, once transformed, the overall size of motion vector plus prediction error is lower than the size of a raw encoding. If the block matching algorithm fails to find a suitable match the prediction error will be considerable. Thus the overall size of motion vector plus prediction error will be greater than the raw encoding.

Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors

Sabine Süsstrunk, Yufan Ren, Peter Arpad Grönquist, Alessio Verardo, Qingyi He

Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person’s expression or identity. Most current DeepFake detection methods analyze each frame independently, ignoring inconsistencies and unnatural movements between frames. Som ...

2024