Physically Compatible 3D Object Modeling from a Single Image
Authors: Minghao Guo, Bohan Wang, Pingchuan Ma, Tianyuan Zhang, Crystal Owens, Chuang Gan, Josh Tenenbaum, Kaiming He, Wojciech Matusik
NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Evaluations on a dataset collected from Objaverse demonstrate that our framework consistently enhances the physical realism of 3D models over existing methods. In this section, we present evidence that our approach enhances the physical compatibility of 3D objects produced using state-of-the-art single-view reconstruction techniques. We conduct a series of quantitative evaluations using five metrics (Sec. 4.1) to compare the physical compatibility of shapes optimized by our framework against those produced by existing methods without our method (Sec. 4.2). We also provide qualitative comparisons to demonstrate to the effectiveness of our approach (Sec. 4.3). |
| Researcher Affiliation | Collaboration | Minghao Guo1, Bohan Wang1 , Pingchuan Ma1, Tianyuan Zhang1, Crystal Elaine Owens1, Chuang Gan2, 3, Joshua B. Tenenbaum1, 4, 5, Kaiming He1, Wojciech Matusik1 1MIT CSAIL, 2UMass Amherst, 3MIT-IBM Waston AI Lab, 4MIT BCS, 5Center for Brains, Minds and Machines |
| Pseudocode | No | The paper includes mathematical formulations and a pipeline diagram (Figure 2), but no explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | https://gmh14.github.io/phys-comp/ |
| Open Datasets | Yes | The evaluation dataset was sourced from Objaverse [9]. [9] M. Deitke, D. Schwenk, J. Salvador, L. Weihs, O. Michel, E. Vander Bilt, L. Schmidt, K. Ehsani, A. Kembhavi, and A. Farhadi. Objaverse: A universe of annotated 3d objects. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13142 13153, 2023. |
| Dataset Splits | No | The paper mentions an 'evaluation dataset' but does not specify distinct training, validation, and test splits with percentages, sample counts, or references to predefined splits for their experiments. |
| Hardware Specification | Yes | Our experiments run on a desktop PC with an AMD Ryzen 9 5950X 16-core CPU and 64GB RAM. |
| Software Dependencies | No | The paper mentions methods and tools like Finite Element Method (FEM), Tet Wild [15], Newton-Raphson solver, and Adam optimizer [17], but does not provide specific version numbers for any software dependencies. |
| Experiment Setup | Yes | The mechanical properties Θ, including Young s modulus E, Poisson s ratio ν, and mass density ρ, are set by users. We use two sets of Young s modulus, E = 5 104Pa and E = 5 105Pa... Poisson s ratio ν = 0.45 and mass density ρ = 1000kg/m3 are consistent across all meshes. We employ the Newton-Raphson solver with line search, setting the maximum number of iterations to be 200. For optimizing Eq. 4, we use gradient descent and allow up to 1000 iterations. |