Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
EA3D: Online Open-World 3D Object Extraction from Streaming Videos
Authors: Xiaoyu Zhou, Jingqi Wang, Yuang Jia, Yongtao Wang, Deqing Sun, Ming-Hsuan Yang
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments across diverse benchmarks and tasks, including photo-realistic rendering, semantic and instance segmentation, 3D bounding box and semantic occupancy estimation, and 3D mesh generation, demonstrate the effectiveness of EA3D. |
| Researcher Affiliation | Collaboration | 1Wangxuan Institute of Computer Technology, Peking University 2Google Deep Mind 3University of California, Merced |
| Pseudocode | No | The paper describes methods in structured text but does not include a clearly labeled pseudocode or algorithm block. |
| Open Source Code | Yes | The project webpage is available at https://github.com/VDIGPKU/EA3D. |
| Open Datasets | Yes | Datasets. We evaluate our method on two benchmarks: LERF [16] dataset comprises in-the-wild scenarios captured with the i Phone App Polycam. The objects in LERF include both common and long-tail categories with different sizes. Scannet [6] is an indoor dataset comprising each annotated with instance-level segmentation and labels across 200 categories. |
| Dataset Splits | Yes | Every fifth frame is used as a test view. |
| Hardware Specification | Yes | All experiments are conducted on a single A100 80GB GPU. |
| Software Dependencies | No | The paper mentions software components like 'Hi Co M', 'Cut3R', 'CLIP', and 'Grounded SAM' but does not provide specific version numbers for these or other ancillary software dependencies, which is required for reproducibility. |
| Experiment Setup | Yes | We implement EA3D based on Hi Co M with a fixed λ1 = 0.25, λ2 = 0.1, and λ3 = 0.15. Each incoming frame is optimized with 100 motion steps, plus another 100 steps after adding new Gaussians. |