# Easi3R: Estimating Disentangled Motion from DUSt3R Without Training

arXiv: https://arxiv.org/abs/2503.24391 · HTML: https://mlsanity.com/paper/2503.24391/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 80 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 30 of 51)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [UniDepth: Universal Monocular Metric Depth Estimation](https://mlsanity.com/paper/2403.18913/) (2024)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos](https://mlsanity.com/paper/2412.04463/) (2024)
- [Visual Geometry Grounded Deep Structure From Motion](https://mlsanity.com/paper/2312.04563/) (2023)
- [Consistent Video Depth Estimation](https://mlsanity.com/paper/2004.15021/) (2020)
- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors](https://mlsanity.com/paper/2412.12392/) (2024)
- [DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos](https://mlsanity.com/paper/2409.02095/) (2024)
- [Monocular Dynamic View Synthesis: A Reality Check](https://mlsanity.com/paper/2210.13445/) (2022)
- [Robust Consistent Video Depth Estimation](https://mlsanity.com/paper/2012.05901/) (2020)
- [BA-Net: Dense Bundle Adjustment Network](https://mlsanity.com/paper/1806.04807/) (2018)

## Built on by (most cited first, 30 of 91)

- [ViPE: Video Pose Engine for 3D Geometric Perception](https://mlsanity.com/paper/2508.10934/) (2025)
- [TTT3R: 3D Reconstruction as Test-Time Training](https://mlsanity.com/paper/2509.26645/) (2025)
- [SpatialVID: A Large-Scale Video Dataset with Spatial Annotations](https://mlsanity.com/paper/2509.09676/) (2025)
- [Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction](https://mlsanity.com/paper/2504.07961/) (2025)
- [SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass](https://mlsanity.com/paper/2508.15769/) (2025)
- [Efficiently Reconstructing Dynamic Scenes One D4RT at a Time](https://mlsanity.com/paper/2512.08924/) (2025)
- [Human3R: Everyone Everywhere All at Once](https://mlsanity.com/paper/2510.06219/) (2025)
- [LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction](https://mlsanity.com/paper/2604.14141/) (2026)
- [MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second](https://mlsanity.com/paper/2507.10065/) (2025)
- [Trace Anything: Representing Any Video in 4D via Trajectory Fields](https://mlsanity.com/paper/2510.13802/) (2025)
- [VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction](https://mlsanity.com/paper/2511.19971/) (2025)
- [VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction](https://mlsanity.com/paper/2601.19887/) (2026)
- [Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey](https://mlsanity.com/paper/2507.14501/) (2025)
- [Test3R: Learning to Reconstruct 3D at Test Time](https://mlsanity.com/paper/2506.13750/) (2025)
- [iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos](https://mlsanity.com/paper/2506.08334/) (2025)
- [RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction](https://mlsanity.com/paper/2512.23437/) (2025)
- [Multi-View 3D Point Tracking](https://mlsanity.com/paper/2508.21060/) (2025)
- [Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis](https://mlsanity.com/paper/2601.14253/) (2026)
- [Reconstructing 4D Spatial Intelligence: A Survey](https://mlsanity.com/paper/2507.21045/) (2025)
- [Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels](https://mlsanity.com/paper/2603.02573/) (2026)
- [PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery](https://mlsanity.com/paper/2603.17571/) (2026)
- [Rig3R: Rig-Aware Conditioning for Learned 3D Reconstruction](https://mlsanity.com/paper/2506.02265/) (2025)
- [TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction](https://mlsanity.com/paper/2601.22615/) (2026)
- [Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT](https://mlsanity.com/paper/2507.08448/) (2025)
- [4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation](https://mlsanity.com/paper/2511.18416/) (2025)
- [DROID-SLAM in the Wild](https://mlsanity.com/paper/2603.19076/) (2026)
- [StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams](https://mlsanity.com/paper/2506.08862/) (2025)
- [Unposed 3DGS Reconstruction with Probabilistic Procrustes Mapping](https://mlsanity.com/paper/2507.18541/) (2025)
- [VGGT-X: When VGGT Meets Dense Novel View Synthesis](https://mlsanity.com/paper/2509.25191/) (2025)
- [C4D: 4D Made from 3D through Dual Correspondences](https://mlsanity.com/paper/2510.14960/) (2025)

## Abstract (arXiv)

Recent advances in DUSt3R have enabled robust estimation of dense point clouds and camera parameters of static scenes, leveraging Transformer network architectures and direct supervision on large-scale 3D datasets. In contrast, the limited scale and diversity of available 4D datasets present a major bottleneck for training a highly generalizable 4D model. This constraint has driven conventional 4D methods to fine-tune 3D models on scalable dynamic video data with additional geometric priors such as optical flow and depths. In this work, we take an opposite path and introduce Easi3R, a simple yet efficient training-free method for 4D reconstruction. Our approach applies attention adaptation during inference, eliminating the need for from-scratch pre-training or network fine-tuning. We find that the attention layers in DUSt3R inherently encode rich information about camera and object motion. By carefully disentangling these attention maps, we achieve accurate dynamic region segmentation, camera pose estimation, and 4D dense point map reconstruction. Extensive experiments on real-world dynamic videos demonstrate that our lightweight attention adaptation significantly outperforms previous state-of-the-art methods that are trained or finetuned on extensive dynamic datasets. Our code is publicly available for research purpose at https://easi3r.github.io/