paper-with-me

Papers

Zero-to-Hero: Zero-Shot Initialization Empowering Reference-Based Video Appearance Editing

2025-05-29 · Tongtong Su, Chengyu Wang, Jun Huang, Dongming Lu

Appearance editing according to user needs is a pivotal task in video editing. Existing text-guided methods often lead to ambiguities regarding user intentions and restrict fine-grained control over editing specific aspects of objects. To overcome these limitations, this paper introduces a novel approach named {Zero-to-Hero}, which focuses on reference-based video editing that disentangles the editing process into two distinct problems. It achieves this by first editing an anchor frame to satisfy user requirements as a reference image and then consistently propagating its appearance across other frames. We leverage correspondence within the original frames to guide the attention mechanism, which is more robust than previously proposed optical flow or temporal modules in memory-friendly video generative models, especially when dealing with objects exhibiting large motions. It offers a solid ZERO-shot initialization that ensures both accuracy and temporal consistency. However, intervention in the attention mechanism results in compounded imaging degradation with over-saturated colors and unknown blurring issues. Starting from Zero-Stage, our Hero-Stage Holistically learns a conditional generative model for vidEo RestOration. To accurately evaluate the consistency of the appearance, we construct a set of videos with multiple appearances using Blender, enabling a fine-grained and deterministic evaluation. Our method outperforms the best-performing baseline with a PSNR improvement of 2.6 dB. The project page is at https://github.com/Tonniia/Zero2Hero.

📄 PDF Abstract BibTeX arXiv:2505.23134

Code (1)

tonniia/zero2hero 공식 구현

Tasks

Optical Flow EstimationVideo EditingVideo Restoration

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
RoIAlign Region of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh…
RoIPool 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents

2026-04-02 · Nikolai Ludwig, Wasi Uddin Ahmad, Somshubra Majumdar, Boris Ginsburg arxiv

We introduce SWE-ZERO to SWE-HERO, a two-stage SFT recipe that achieves state-of-the-art results on SWE-bench by distilling open-weight frontier LLMs. Our pipeline replaces resource-heavy dependencies with an evolutionar…

Zero is Not Hero Yet: Benchmarking Zero-Shot Performance of LLMs for Financial Tasks

2023-05-26 · Agam Shah, Sudheer Chava

Recently large language models (LLMs) like ChatGPT have shown impressive performance on many natural language processing tasks with zero-shot. In this paper, we investigate the effectiveness of zero-shot LLMs in the fina…

Benchmarking

From Zero to Hero: Cold-Start Anomaly Detection

2024-05-30 · Tal Reiss, George Kour, Naama Zwerdling, Ateret Anaby-Tavor 외

When first deploying an anomaly detection system, e.g., to detect out-of-scope queries in chatbots, there are no observed data, making data-driven approaches ineffective. Zero-shot anomaly detection methods offer a solut…

Anomaly DetectionCold-Start Anomaly Detectionzero-shot anomaly detection

Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data

2022-05-16 · NAACL (WNU) 2022 7 · Dominik Stammbach, Maria Antoniak, Elliott Ash

This paper shows how to use large-scale pre-trained language models to extract character roles from narrative texts without training data. Queried with a zero-shot question-answering prompt, GPT-3 can identify the hero, …

ArticlesQuestion Answering

Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering

2024-05-29 · Ido Sobol, Chenfeng Xu, Or Litany

Generating realistic images from arbitrary views based on a single source image remains a significant challenge in computer vision, with broad applications ranging from e-commerce to immersive virtual experiences. Recent…

DenoisingImage GenerationNovel View Synthesis