# Object-WIPER : Training-Free Object and Associated Effect Removal in Videos

arXiv: https://arxiv.org/abs/2601.06391 · HTML: https://mlsanity.com/paper/2601.06391/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 46 references that are in the map.
- First posted on arXiv 10 Jan 2026.

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [FateZero: Fusing Attentions for Zero-shot Text-based Video Editing](https://mlsanity.com/paper/2303.09535/) (2023)
- [TokenFlow: Consistent Diffusion Features for Consistent Video Editing](https://mlsanity.com/paper/2307.10373/) (2023)
- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [Pix2Video: Video Editing using Image Diffusion](https://mlsanity.com/paper/2303.12688/) (2023)
- [TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement](https://mlsanity.com/paper/2306.08637/) (2023)
- [Taming Rectified Flow for Inversion and Editing](https://mlsanity.com/paper/2411.04746/) (2024)
- [ProPainter: Improving Propagation and Transformer for Video Inpainting](https://mlsanity.com/paper/2309.03897/) (2023)
- [FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing](https://mlsanity.com/paper/2310.05922/) (2023)
- [D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video](https://mlsanity.com/paper/2205.15838/) (2022)
- [Deep Flow-Guided Video Inpainting](https://mlsanity.com/paper/1905.02884/) (2019)
- [RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models](https://mlsanity.com/paper/2312.04524/) (2023)
- [Deep Video Inpainting](https://mlsanity.com/paper/1905.01639/) (2019)
- [Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN](https://mlsanity.com/paper/1904.10247/) (2019)
- [VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control](https://mlsanity.com/paper/2503.05639/) (2025)
- [DiffuEraser: A Diffusion Model for Video Inpainting](https://mlsanity.com/paper/2501.10018/) (2025)
- [Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance](https://mlsanity.com/paper/2412.12974/) (2024)
- [ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features](https://mlsanity.com/paper/2502.04320/) (2025)
- [KV-Edit: Training-Free Image Editing for Precise Background Preservation](https://mlsanity.com/paper/2502.17363/) (2025)
- [Video Inpainting of Complex Scenes](https://mlsanity.com/paper/1503.05528/) (2015)
- [UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models](https://mlsanity.com/paper/2504.13109/) (2025)
- [Generative Omnimatte: Learning to Decompose Video into Layers](https://mlsanity.com/paper/2411.16683/) (2024)

## Built on by (most cited first, 6 of 6)

- [VOID: Video Object and Interaction Deletion](https://mlsanity.com/paper/2604.02296/) (2026)
- [From Ideal to Real: Stable Video Object Removal under Imperfect Conditions](https://mlsanity.com/paper/2603.09283/) (2026)
- [From Understanding to Erasing: Towards Complete and Stable Video Object Removal](https://mlsanity.com/paper/2604.01693/) (2026)
- [PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media](https://mlsanity.com/paper/2605.14534/) (2026)
- [EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal](https://mlsanity.com/paper/2608.05565/) (2026)
- [TripleFlow: Training-Free Video Object Removal by Bridging Residual Editing and Native Generation](https://mlsanity.com/paper/2609.39157/) (2026)

## Abstract (arXiv)

In this paper, we introduce Object-WIPER, a training-free framework for removing dynamic objects and their associated visual effects from videos, and inpainting them with semantically consistent and temporally coherent content. Our approach leverages a pre-trained text-to-video diffusion transformer (DiT). Given an input video, a user-provided object mask, and query tokens describing the target object and its effects, we localize relevant visual tokens via visual-text cross-attention and visual self-attention. This produces an intermediate effect mask that we fuse with the user mask to obtain a final foreground token mask to replace. We first invert the video through the DiT to obtain structured noise, then reinitialize the masked tokens with Gaussian noise while preserving background tokens. During denoising, we copy values for the background tokens saved during inversion to maintain scene fidelity. To address the lack of suitable evaluation, we introduce a new object removal metric that rewards temporal consistency among foreground tokens across consecutive frames, coherence between foreground and background tokens within each frame, and dissimilarity between the input and output foreground tokens. Experiments on DAVIS and a newly curated real-world associated effect benchmark (WIPER-Bench) show that Object-WIPER surpasses both training-based and training-free baselines in terms of the metric, achieving clean removal and temporally stable reconstruction without any retraining. Our new benchmark, source code, and pre-trained models will be publicly available.