# Estimating more camera poses for ego-centric videos is essential for VQ3D

arXiv: https://arxiv.org/abs/2211.10284 · HTML: https://mlsanity.com/paper/2211.10284/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 9 references that are in the map.
- First posted on arXiv 18 Nov 2022.

## Builds on (most cited first, 7 of 7)

- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Embodied Question Answering](https://mlsanity.com/paper/1711.11543/) (2017)
- [Episodic Memory Question Answering](https://mlsanity.com/paper/2205.01652/) (2022)
- [Negative Frames Matter in Egocentric Visual Query 2D Localization](https://mlsanity.com/paper/2208.01949/) (2022)

## Built on by (most cited first, 3 of 3)

- [EgoCOL: Egocentric Camera pose estimation for Open-world 3D object Localization @Ego4D challenge 2023](https://mlsanity.com/paper/2306.16606/) (2023)
- [Hybrid Structure-from-Motion and Camera Relocalization for Enhanced Egocentric Localization](https://mlsanity.com/paper/2407.08023/) (2024)
- [EgoHieraLoc: A Cortically Inspired Hierarchical Segmentation-Guided Framework for Egocentric Visual Query Localization](https://mlsanity.com/paper/2608.09656/) (2026)

## Abstract (arXiv)

Visual queries 3D localization (VQ3D) is a task in the Ego4D Episodic Memory Benchmark. Given an egocentric video, the goal is to answer queries of the form "Where did I last see object X?", where the query object X is specified as a static image, and the answer should be a 3D displacement vector pointing to object X. However, current techniques use naive ways to estimate the camera poses of video frames, resulting in a low query with pose (QwP) ratio, thus a poor overall success rate. We design a new pipeline for the challenging egocentric video camera pose estimation problem in our work. Moreover, we revisit the current VQ3D framework and optimize it in terms of performance and efficiency. As a result, we get the top-1 overall success rate of 25.8% on VQ3D leaderboard, which is two times better than the 8.7% reported by the baseline.