# EraserDiT: Fast Video Inpainting with Diffusion Transformer Model

arXiv: https://arxiv.org/abs/2506.12853 · HTML: https://mlsanity.com/paper/2506.12853/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 16 of its 18 references that are in the map.
- First posted on arXiv 15 Jun 2025.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 16 of 16)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [ProPainter: Improving Propagation and Transformer for Video Inpainting](https://mlsanity.com/paper/2309.03897/) (2023)
- [Learning Joint Spatial-Temporal Transformations for Video Inpainting](https://mlsanity.com/paper/2007.10247/) (2020)
- [FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting](https://mlsanity.com/paper/2109.02974/) (2021)
- [DiffuEraser: A Diffusion Model for Video Inpainting](https://mlsanity.com/paper/2501.10018/) (2025)
- [MiniMax-Remover: Taming Bad Noise Helps Video Object Removal](https://mlsanity.com/paper/2505.24873/) (2025)
- [Elevating Flow-Guided Video Inpainting with Reference Generation](https://mlsanity.com/paper/2412.08975/) (2024)

## Built on by (most cited first, 5 of 5)

- [CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Video Subtitle Removal](https://mlsanity.com/paper/2603.21901/) (2026)
- [SEDiT: Mask-Free Video Subtitle Erasure via One-step Diffusion Transformer](https://mlsanity.com/paper/2605.14894/) (2026)
- [DualEraser: Joint Video Object and Effect Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver](https://mlsanity.com/paper/2605.30045/) (2026)
- [Transformer-Based Inpainting for Real-Time 3D Streaming in Sparse Multi-Camera Setups](https://mlsanity.com/paper/2603.05507/) (2026)
- [VOR-Bench: A Human Perception-Driven Benchmark for Video Object Removal](https://mlsanity.com/paper/2609.16878/) (2026)

## Abstract (arXiv)

Video object removal and inpainting are critical tasks in the fields of computer vision and multimedia processing, aimed at restoring missing or corrupted regions in video sequences. Traditional methods predominantly rely on flow-based propagation and spatio-temporal Transformers, but these approaches face limitations in effectively leveraging long-term temporal features and ensuring temporal consistency in the completion results, particularly when dealing with large masks. Consequently, performance on extensive masked areas remains suboptimal. To address these challenges, this paper introduces a novel video inpainting approach leveraging the Diffusion Transformer (DiT). DiT synergistically combines the advantages of diffusion models and transformer architectures to maintain long-term temporal consistency while ensuring high-quality inpainting results. We propose a Circular Position-Shift strategy to further enhance long-term temporal consistency during the inference stage. Additionally, the proposed method interactively removes specified objects, and generates corresponding prompts. In terms of processing speed, it takes only 65 seconds (testing on one NVIDIA H800 GPU) to complete a video with a resolution of 2160 × 2100 with 97 frames without any acceleration method. Experimental results indicate that the proposed method demonstrates superior performance in content fidelity, texture restoration, and temporal consistency. Project page:https://jieliu95.github.io/EraserDiTdemo/