1 code implementation • 14 Mar 2024 • Jaewoo Jung, Jisang Han, Honggyu An, Jiwon Kang, Seonghoon Park, Seungryong Kim
Through extensive analysis of SfM initialization in the frequency domain and analysis of a 1D regression task with multiple 1D Gaussians, we propose a novel optimization strategy dubbed RAIN-GS (Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting), that successfully trains 3D Gaussians from random point clouds.
1 code implementation • 12 Dec 2023 • Sunghwan Hong, Jaewoo Jung, Heeseong Shin, Jiaolong Yang, Seungryong Kim, Chong Luo
This work delves into the task of pose-free novel view synthesis from stereo pairs, a challenging and pioneering task in 3D vision.
1 code implementation • 2 Dec 2023 • Jaewoo Jung, Jisang Han, Jiwon Kang, Seongchan Kim, Min-Seop Kwak, Seungryong Kim
We formulate few-shot NeRF into a teacher-student framework to guide the network to learn a more robust representation of the scene by training the student with additional pseudo labels generated from the teacher.
1 code implementation • 17 Oct 2023 • Gyuseong Lee, Wooseok Jang, Jin Hyeon Kim, Jaewoo Jung, Seungryong Kim
By using both PEFT and MoA methods, we effectively alleviate the performance deterioration caused by distribution shifts and achieve state-of-the-art performance on diverse DG benchmarks.