AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Post-Training Quantization for Video Matting

Tianrui Zhu, Houyuan Chen, Ruihao Gong, Michele Magno, Haotong Qin, Kai Zhang

ICLR 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs

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 Global Affine Calibration (GAC) to BRECQ (ablation)BRECQ · VM 512x288, W4A4Alpha MAD: 168.34 -> 50.75Improved
add GAC to QDrop (ablation)QDrop · VM 512x288, W4A4Alpha MAD: 24.36 -> 22.01Improved
add Optical Flow Assistance (OFA) on top of BRECQ+GAC (ablation)BRECQ+GAC · VM 512x288, W4A4Alpha MAD: 50.75 -> 46.16Improved
add OFA on top of BRECQ+GAC (ablation)BRECQ+GAC · VM 512x288, W4A4DTSSD: 8.01 -> 3.15Improved
add OFA on top of QDrop+GAC (ablation)QDrop+GAC · VM 512x288, W4A4Alpha MSE (x1e-3): 11.85 -> 13.80Hurt
add OFA on top of QDrop+GAC (ablation)QDrop+GAC · VM 512x288, W4A8Alpha MSE (x1e-3): 4.43 -> 4.54No clear effect
use block-wise initial quantization (BIQ) instead of naive full-network quantization (ablation)PTQ4VM · VM, W4A4 and W4A8Alpha error convergenceImproved
apply Cross-Layer Equalization and bias absorption before quantizationRVM PTQ · VMaccuracyNo clear effect
use PTQ4VM instead of QDrop at 4-bit weightsRVM · VM 512x288, W4A8Alpha MAD: 11.72 -> 10.77Improved
use PTQ4VM at W8A8 instead of FP32RVM · D646 512x512, W8A8Alpha MAD: 6.63 -> 7.14Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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