AI Paper Atlas

Research map / Video / Video segmentation and tracking

DeepLandscape: Adversarial Modeling of Landscape Videos

Elizaveta Logacheva, Roman Suvorov, Oleg Khomenko, Anton Mashikhin, Victor Lempitsky

ECCV 2020 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 28 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 decaying discriminator frequency instead of freq=0.5 (ablation)pairwise discriminator · Discriminator balancing (128px)FID: 82.10 -> 56.13Improved
add decaying discriminator frequency instead of freq=0.3 (ablation)pairwise discriminator · Discriminator balancing (128px)FID: 63.48 -> 56.13Improved
use decay instead of freq=0.1 (ablation)pairwise discriminator · Discriminator balancing (128px)User study R: -0.03Improved
use decay instead of freq=0.1 (ablation)pairwise discriminator · Discriminator balancing (128px)FID: 54.15 -> 56.13No clear effect
add encoder initialization (E) to model-only optimization (ablation)inference procedure · Inference ablationSSIM: 0.95 -> 0.54Hurt
add optimization after encoder (EO vs E) (ablation)inference procedure · Inference ablationLPIPS: 0.43 -> 0.07Improved
add tying W to initial values (EOI vs EO) (ablation)inference procedure · Inference ablationSky optical flow: 1.5 -> 2.5Improved
add generator fine-tuning (EOIF vs EOI) (ablation)inference procedure · Inference ablationLPIPS: 0.11 -> 0.04Improved
add segmentation guidance (EOIFS vs EOIF) (ablation)inference procedure · Inference ablationSky optical flow: 2.3 -> 2.6Mixed
use EOIF instead of I2S inversion (ablation)inference procedure · Inference ablationLPIPS: 0.18 -> 0.04Improved
finetune Animating Landscape on our video dataset (ablation)Animating Landscape · Animated Landscape on our video dataUser preference: 0.68 -> 0.32Hurt
finetune Animating Landscape on our video dataset (ablation)Animating Landscape · Animated Landscape on our video dataFVD: 162 -> 159No clear effect

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