Application Space and the Rate-Distortion-Complexity Analysis of Neural Video CODECs
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918136856444928 |
|---|---|
| author | de Queiroz, Ricardo L. Garcia, Diogo C. Chen, Yi-Hsin Conceição, Ruhan Peng, Wen-Hsiao Agostini, Luciano V. |
| author_facet | de Queiroz, Ricardo L. Garcia, Diogo C. Chen, Yi-Hsin Conceição, Ruhan Peng, Wen-Hsiao Agostini, Luciano V. |
| contents | We study the decision-making process for choosing video compression systems through a rate-distortion-complexity (RDC) analysis. We discuss the 2D Bjontegaard delta (BD) metric and formulate generalizations in an attempt to extend its notions to the 3D RDC volume. We follow that discussion with another one on the computation of metrics in the RDC volume, and on how to define and measure the cost of a coder-decoder (codec) pair, where the codec is characterized by a cloud of points in the RDC space. We use a Lagrangian cost $D+λR + γC$, such that choosing the best video codec among a number of candidates for an application demands selecting appropriate $(λ, γ)$ values. Thus, we argue that an application may be associated with a $(λ, γ)$ point in the application space. An example streaming application was given as a case study to set a particular point in the $(λ, γ)$ plane. The result is that we can compare Lagrangian costs in an RDC volume for different codecs for a given application. Furthermore, we can span the plane and compare codecs for the entire application space filled with different $(λ, γ)$ choices. We then compared several state-of-the-art neural video codecs using the proposed metrics. Results are informative and surprising. We found that, within our RDC computation constraints, only four neural video codecs came out as the best suited for any application, depending on where its desirable $(λ, γ)$ lies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05929 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Application Space and the Rate-Distortion-Complexity Analysis of Neural Video CODECs de Queiroz, Ricardo L. Garcia, Diogo C. Chen, Yi-Hsin Conceição, Ruhan Peng, Wen-Hsiao Agostini, Luciano V. Image and Video Processing We study the decision-making process for choosing video compression systems through a rate-distortion-complexity (RDC) analysis. We discuss the 2D Bjontegaard delta (BD) metric and formulate generalizations in an attempt to extend its notions to the 3D RDC volume. We follow that discussion with another one on the computation of metrics in the RDC volume, and on how to define and measure the cost of a coder-decoder (codec) pair, where the codec is characterized by a cloud of points in the RDC space. We use a Lagrangian cost $D+λR + γC$, such that choosing the best video codec among a number of candidates for an application demands selecting appropriate $(λ, γ)$ values. Thus, we argue that an application may be associated with a $(λ, γ)$ point in the application space. An example streaming application was given as a case study to set a particular point in the $(λ, γ)$ plane. The result is that we can compare Lagrangian costs in an RDC volume for different codecs for a given application. Furthermore, we can span the plane and compare codecs for the entire application space filled with different $(λ, γ)$ choices. We then compared several state-of-the-art neural video codecs using the proposed metrics. Results are informative and surprising. We found that, within our RDC computation constraints, only four neural video codecs came out as the best suited for any application, depending on where its desirable $(λ, γ)$ lies. |
| title | Application Space and the Rate-Distortion-Complexity Analysis of Neural Video CODECs |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2509.05929 |