AI Paper Atlas

Research map / Video / Video segmentation and tracking

JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video

Soo Ye Kim, Jihyong Oh, Munchurl Kim

AAAI 2020 · Video › Video segmentation and tracking · approach: Space-time video super-resolution · 81 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add the DR subnet to IR using division-based detail decomposition (ablation)JSInet · JSInet subnet ablationPSNR (dB): 0.44 dB gainImproved
Add the LCE subnet to IR + DR (ablation)JSInet · JSInet subnet ablationPSNR (dB): 0.11 dBImproved
Use division rather than subtraction to decompose the detail layer (ablation)JSInet with DR and LCE · JSInet subnet ablationPSNR (dB): 0.31 dBImproved
Remove concatenation of DR intermediate features (ablation)JSInet IR + DR · JSInet subnet ablationPSNR (dB): 0.02 dB dropHurt
Concatenate LCE intermediate features with IR and DR features (ablation)JSInet · JSInet subnet ablationPSNR (dB): 0.25 dB dropHurt
Stack the input image with the detail layer as DR input (ablation)JSInet IR + DR · JSInet subnet ablationPSNR (dB)No clear effect
Use location-varying filter generation for DR instead of direct detail reconstruction (ablation)JSInet IR + DR · JSInet IR/DR filter ablationPSNR (dB): 0.15 dBImproved
Use filter generation for IR rather than direct reconstruction (ablation)JSInet IR + DR · JSInet IR/DR filter ablationPSNR (dB): 35.88 -> 34.14Hurt
Use 1D separable kernels instead of 2D local filters for LCE (ablation)JSInet LCE subnet · JSInet filter ablationPSNR (dB): 0.07 dBHurt
Add feature-matching loss to basic adversarial training (ablation)JSI-GAN · 4K HDR dataset ×2PSNR (dB): 1.9dBImproved
Add feature-matching loss to basic adversarial training (ablation)JSI-GAN · 4K HDR dataset ×4PSNR (dB): 1.37dBImproved
Add detail-component adversarial and feature-matching losses (ablation)JSI-GAN with feature matching · 4K HDR dataset ×2PSNR (dB): 35.63 -> 35.73Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy