# EPRecon: An Efficient Framework for Real-Time Panoptic 3D Reconstruction from Monocular Video

arXiv: https://arxiv.org/abs/2409.01807 · HTML: https://mlsanity.com/paper/2409.01807/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 68 references that are in the map.
- First posted on arXiv 3 Sep 2024.

## Builds on (most cited first, 5 of 5)

- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [DPSNet: End-to-end Deep Plane Sweep Stereo](https://mlsanity.com/paper/1905.00538/) (2019)
- [Fully Sparse 3D Occupancy Prediction](https://mlsanity.com/paper/2312.17118/) (2023)
- [Panoptic-FlashOcc: An Efficient Baseline to Marry Semantic Occupancy with Panoptic via Instance Center](https://mlsanity.com/paper/2406.10527/) (2024)
- [Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation](https://mlsanity.com/paper/2401.05925/) (2024)

## Built on by (most cited first, 4 of 4)

- [PanSt3R: Multi-view Consistent Panoptic Segmentation](https://mlsanity.com/paper/2506.21348/) (2025)
- [MoonSeg3R: Monocular Online Zero-Shot Segment Anything in 3D with Reconstructive Foundation Priors](https://mlsanity.com/paper/2512.15577/) (2025)
- [Image-Plane Geometric Decoding for View-Invariant Indoor Scene Reconstruction](https://mlsanity.com/paper/2509.25744/) (2025)
- [VFM-Recon: Unlocking Cross-Domain Scene-Level Neural Reconstruction with Scale-Aligned Foundation Priors](https://mlsanity.com/paper/2603.12657/) (2026)

## Abstract (arXiv)

Panoptic 3D reconstruction from a monocular video is a fundamental perceptual task in robotic scene understanding. However, existing efforts suffer from inefficiency in terms of inference speed and accuracy, limiting their practical applicability. We present EPRecon, an efficient real-time panoptic 3D reconstruction framework. Current volumetric-based reconstruction methods usually utilize multi-view depth map fusion to obtain scene depth priors, which is time-consuming and poses challenges to real-time scene reconstruction. To address this issue, we propose a lightweight module to directly estimate scene depth priors in a 3D volume for reconstruction quality improvement by generating occupancy probabilities of all voxels. In addition, compared with existing panoptic segmentation methods, EPRecon extracts panoptic features from both voxel features and corresponding image features, obtaining more detailed and comprehensive instance-level semantic information and achieving more accurate segmentation results. Experimental results on the ScanNetV2 dataset demonstrate the superiority of EPRecon over current state-of-the-art methods in terms of both panoptic 3D reconstruction quality and real-time inference. Code is available at https://github.com/zhen6618/EPRecon.