AI Paper Atlas

Research map / Video / Video segmentation and tracking

MH-LVC: Multi-Hypothesis Temporal Prediction for Learned Conditional Residual Video Coding

Huu-Tai Phung, Zong-Lin Gao, Yi-Chen Yao, Kuan-Wei Ho, Yi-Hsin Chen, Yu-Hsiang Lin, Alessandro Gnutti, Wen-Hsiao Peng

ICCV 2025 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 3 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 spatial gating to long/short-term feature fusion (ablation)MH-LVC · HEVC Class B-EBD-rate PSNR-RGB (%): -4.2, -5.9, -5.5, -13.1 vs 0.0 (Class B, C, D, E)Improved
use spatial gating instead of CNN-based fusion (ablation)MH-LVC LSTP · HEVC Class BBD-rate PSNR-RGB (%): -2.1 -> -4.2Improved
use spatial gating instead of CNN-based fusion (ablation)MH-LVC LSTP · HEVC Class EBD-rate PSNR-RGB (%): -9.1 -> -13.1Improved
add a second long-term key frame (MH-LVC-2 vs MH-LVC-1) (ablation)MH-LVC · UVGBD-rate PSNR-RGB (%): -9.6 -> -12.5Improved
add a second long-term key frame (MH-LVC-2 vs MH-LVC-1) (ablation)MH-LVC · HEVC-BBD-rate PSNR-RGB (%): -12.8 -> -15.7Improved
add a third long-term key frame beyond two (ablation)MH-LVC · HEVC-BBD-rate PSNR-RGB (%): -3.4 -> -3.8No clear effect
add a third long-term key frame beyond two (encoding cost) (ablation)MH-LVC · HEVC-BEncoding kMAC/pixel: 2611 -> 3716 kMAC/pixelHurt
increase mini-GOP size from 4 to 16 (ablation)MH-LVC · HEVC-BBD-rate PSNR-RGB (%): 0.0 -> 2.9Hurt
increase mini-GOP size from 4 to 16 (ablation)MH-LVC · UVGBD-rate PSNR-RGB (%): 0.0 -> 2.1Hurt
use long-short prediction (LS) instead of short-short (SS) (ablation)MH-LVC · HEVC-BBD-rate PSNR-RGB (%): 14.6 -> 0.0Improved
use long-short prediction (LS) instead of two previous frames (TP) (ablation)MH-LVC · HEVC-BBD-rate PSNR-RGB (%): 3.3 -> 0.0Improved
use explicit two-frame buffering (MH-LVC-1) instead of implicit TCM buffering (ablation)MH-LVC-1 · UVG, HEVC-B, MCL-JCVBD-rate PSNR-RGB (%): 7.8, 3.2, 8.9 BD-rate for TCM vs 0.0Improved

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