ZeroShape: Data Curation Details - Synthetic Training Dataset Generation and More

3 Jan 2025

In this section, we describe our data generation procedure for training and rendering the object scans from OmniObject3D

ZeroShape: The Inference on AI-Generated Images

3 Jan 2025

To test the out-of-domain generalization ability, we generate images of imaginary objects as the input to our model (see Fig. 10).

ZeroShape: Additional Qualitative Comparisons You Should Know About

3 Jan 2025

We show additional qualitative results on OmniObject3D, Ocrtoc3D, and Pix3D in Fig. 7, Fig. 8 and Fig. 9, respectively.

ZeroShape: What We Can Conclude From This Strong Regression-Based Model

2 Jan 2025

We present a strong regression-based model for zero-shot shape reconstruction. The core of our model is an intermediate representation of the 3D visible surface

ZeroShape: The Limitations We Are Facing

2 Jan 2025

Due to computational resource limitations, we are not able to process and train our model on the full Objaverse dataset.

Zero Shape: The Qualitative Results of Different Methods and Our Ablation Study

2 Jan 2025

We show qualitative results of different methods in Fig. 5. Generative approaches such as Point-E and Shap-E tend to have sharper surfaces

ZeroShape: A Comparison to SOTA Methods

1 Jan 2025

We compare our approach to other state-of-the-art methods on the benchmark we curated. We now present and analyze the quantitative results for each dataset.

Introducing ZeroShape's Baselines: The 5 State-of-the-Art Baselines We Considered

1 Jan 2025

We consider five state-of-the-art baselines for shape reconstruction, SS3D, MCC, Point-E, Shap-E and OpenLRM.

ZeroShape: The Metrics and Evaluation Protocol That We Used

1 Jan 2025

In this section, we present our experiments, which include state-of-the-art comparisons and ablations.