EgoMo3R: Joint Egocentric Motion and Scene Reconstruction
cs.CV, cs.AI
Submitted: 2026-11-01
Updated: 2026-11-01
Project page: https://chaitanya100100.github.io/EgoMo3R/Abstract
Terminology
Sources
- MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation
- Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
- Human3R: Everyone Everywhere All at Once
- OmniEgoCap: Device-Agnostic Sequence-Level Egocentric Motion Reconstruction
- Diffusion Posterior Sampling for General Noisy Inverse Problems
- Project Aria: A New Tool for Egocentric Multi-Modal AI Research
- ViPE: Video Pose Engine for 3D Geometric Perception
- Optimizing Diffusion Noise Can Serve As Universal Motion Priors
- Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling
- Joint Optimization for 4D Human-Scene Reconstruction in the Wild
- DPoser: Diffusion Model as Robust 3D Human Pose Prior
- A Variational Perspective on Solving Inverse Problems with Diffusion Models
- Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance
- SAM 2: Segment Anything in Images and Videos
- Human Motion Diffusion as a Generative Prior
- MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
- MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
- Diffusion State-Guided Projected Gradient for Inverse Problems
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs