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..
4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
Authors: Mengqi Guo, Bo Xu, Yanyan Li, Gim Hee Lee
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on real-world dynamic datasets demonstrate that our approach achieves up to 1.8d B PSNR improvement over state-of-the-art methods, particularly in challenging scenarios with large dynamic objects, while reducing computational requirements by 5 compared to previous dynamic scene representations. |
| Researcher Affiliation | Academia | Mengqi Guo1, Bo Xu2, Yanyan Li1, Gim Hee Lee1 1National University of Singapore 2Wuhan University EMAIL |
| Pseudocode | No | The paper describes the methods in narrative text and uses diagrams (e.g., Figure 2 and Figure 5) to illustrate the pipeline and optimization process, but does not provide a structured pseudocode or algorithm block. |
| Open Source Code | No | The paper will provide open access to the data and code after accepted. |
| Open Datasets | Yes | We evaluate our approach on three representative datasets: Hyper Ne RF s dataset [41], Dy Ne RF dataset [28], and the MPI Sintel dataset [6]. |
| Dataset Splits | No | The paper mentions using specific datasets (Hyper Ne RF s, Dy Ne RF, MPI Sintel) and states 'We use only one camera view for training, treating it as a monocular sequence' for the Dy Ne RF dataset. However, it does not explicitly provide details about the training, validation, or test splits for any of the datasets used. |
| Hardware Specification | Yes | All experiments run on a single NVIDIA RTX3090 GPU. |
| Software Dependencies | No | The paper mentions using several pre-trained models and frameworks such as 'Vi T-based transformer', 'SAM2 [43]', 'DUSt3R [56]', 'Mon ST3R [71]', and 'SEA-RAFT [57]', but does not specify version numbers for these software components or any underlying libraries (e.g., PyTorch, TensorFlow, Python versions). |
| Experiment Setup | Yes | The Motion-Aware Gaussian Splatting uses 512 control points, optimized using Adam with learning rates from 1e-4 to 1e-7 (exponential decay). |