Sangeek Hyun, Jae-Pil Heo
We lifted 16 functions out of this paper's own repositories and ran 11 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| hse1032/Adversarial-Generation-of-Hierarchical-Gaussians-for-3D-Generative-Model | canonical | 11 of 16 |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Most advances in 3D Generative Adversarial Networks (3D GANs) largely depend on ray casting-based volume rendering, which incurs demanding rendering costs. One promising alternative is rasterization-based 3D Gaussian Splatting (3D-GS), providing a much faster rendering speed and explicit 3D representation. In this paper, we exploit Gaussian as a 3D representation for 3D GANs by leveraging its efficient and explicit characteristics. However, in an adversarial framework, we observe that a naïve generator architecture suffers from training instability and lacks the capability to adjust the scale of Gaussians. This leads to model divergence and visual artifacts due to the absence of proper guidance for initialized positions of Gaussians and densification to manage their scales adaptively. To address these issues, we introduce GSGAN, a generator architecture with a hierarchical multiscale Gaussian representation that effectively regularizes the position and scale of generated Gaussians. Specifically, we design a hierarchy of Gaussians where finerlevel Gaussians are parameterized by their coarser-level counterparts; the position of finer-level Gaussians would be located near their coarser-level counterparts, and the scale would monotonically decrease as the level becomes finer, modeling both coarse and fine details of the 3D scene. Experimental results demonstrate that ours achieves a significantly faster rendering speed (×100) compared to state-of-the-art 3D consistent GANs with comparable 3D generation capability. Project page: https://hse1032.github.io/gsgan.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.02968")
get_code_for_paper("2406.02968")
have("2406.02968")
Connect an agent — have() is free.