Publications

1000FPS+ Novel View Synthesis from End-to-End Opaque Triangle Optimization

Published in International Conference on 3D Vision (3DV) 2026, 2026

End-to-end optimization of disjoint opaque triangles for scene-level novel view synthesis, achieving 1000+ FPS rendering with standard graphics engine compatibility.

Recommended citation: Yan, Z., Low, W. F., Huang, T., & Lee, G. H. (2026). "1000FPS+ Novel View Synthesis from End-to-End Opaque Triangle Optimization." 3DV 2026. https://openreview.net/forum?id=EFGCajKzQt

Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering

Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, 2025

Proposed an innovative algorithm of 3D novel view synthesis under variable resolutions and distances.

Recommended citation: Yan, Z., Low, W. F., Chen, Y., & Lee, G. H. (2024). "Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering." CVPR 2024. https://arxiv.org/abs/2311.17089

NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects

Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, 2025

Proposed a novel algorithm to generate novel views of specular objects under non-rigid motion.

Recommended citation: Yan, Z., Li, C., & Lee, G. H. (2023). "NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects." CVPR 2023. https://arxiv.org/abs/2303.14435

OD-NeRF: Efficient Training of On-the-Fly Dynamic Neural Radiance Fields

Published in International Conference on 3D Vision (3DV) 2025, 2025

Proposed the first efficient on-the-fly dynamic neural radiance field for real-time reconstruction.

Recommended citation: Yan, Z., Li, C., & Lee, G. H. (2025). "OD-NeRF: Efficient Training of On-the-Fly Dynamic Neural Radiance Fields." 3DV 2025. https://arxiv.org/abs/2305.14831

Animate124: Animating One Image to 4D Dynamic Scene

Published in arXiv preprint, 2023

Proposed a 4D generation algorithm from single image using multi-view video generation model and 2D-to-4D distillation.

Recommended citation: Zhao, Y., Yan, Z., Xie, E., Hong, L., Li, Z., & Lee, G. H. (2023). "Animate124: Animating One Image to 4D Dynamic Scene." arXiv preprint arXiv:2311.14603. https://arxiv.org/abs/2311.14603

GNeSF: Generalizable Neural Semantic Fields

Published in Conference on Neural Information Processing Systems (NeurIPS) 2023, 2023

Proposed a pre-trained generalizable neural network for simultaneous geometry and semantic 3D predictions from multi-view images.

Recommended citation: Chen, H., Li, C., Guo, M., Yan, Z., & Lee, G. H. (2023). "GNeSF: Generalizable Neural Semantic Fields." NeurIPS 2023. https://arxiv.org/abs/2310.15712

Yan Zhiwen