Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
173 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

3DGEN: A GAN-based approach for generating novel 3D models from image data (2312.08094v1)

Published 13 Dec 2023 in cs.CV

Abstract: The recent advances in text and image synthesis show a great promise for the future of generative models in creative fields. However, a less explored area is the one of 3D model generation, with a lot of potential applications to game design, video production, and physical product design. In our paper, we present 3DGEN, a model that leverages the recent work on both Neural Radiance Fields for object reconstruction and GAN-based image generation. We show that the proposed architecture can generate plausible meshes for objects of the same category as the training images and compare the resulting meshes with the state-of-the-art baselines, leading to visible uplifts in generation quality.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (12)
  1. Carla: An open urban driving simulator, 2017. URL https://arxiv.org/abs/1711.03938.
  2. Generative adversarial networks, 2014. URL https://arxiv.org/abs/1406.2661.
  3. Implicit geometric regularization for learning shapes, 2020. URL https://arxiv.org/abs/2002.10099.
  4. Gans trained by a two time-scale update rule converge to a local nash equilibrium. In Advances in Neural Information Processing Systems, pages 6626–6637, 2017.
  5. Marching cubes: A high resolution 3d surface construction algorithm. ACM siggraph computer graphics, 21(4):163–169, 1987.
  6. Which training methods for gans do actually converge? 2018. doi: 10.48550/ARXIV.1801.04406. URL https://arxiv.org/abs/1801.04406.
  7. Nerf: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM, 65(1):99–106, 2021.
  8. Unisurf: Unifying neural implicit surfaces and radiance fields for multi-view reconstruction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 5589–5599, 2021.
  9. Photoshape. ACM Transactions on Graphics, 37(6):1–12, dec 2018. doi: 10.1145/3272127.3275066. URL https://doi.org/10.1145%2F3272127.3275066.
  10. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 2022.
  11. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10684–10695, 2022.
  12. Graf: Generative radiance fields for 3d-aware image synthesis. Advances in Neural Information Processing Systems, 33:20154–20166, 2020.

Summary

We haven't generated a summary for this paper yet.