Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation
Seungjun Oh, Younggeun Lee, Hyejin Jeon +1
Recent advancements in dynamic 3D scene reconstruction have shown promising results, enabling high-fidelity 3D novel view synthesis with improved temporal consistency. Among these,…
cs.CV2024
Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction
Seungtae Nam, Xiangyu Sun, Gyeongjin Kang +3
Generalized feed-forward Gaussian models have achieved significant progress in sparse-view 3D reconstruction by leveraging prior knowledge from large multi-view datasets. However,…
cs.CV2024
CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis
Gyeongjin Kang, Younggeun Lee, Seungjun Oh +1
Neural Radiance Fields (NeRF) have achieved huge success in effectively capturing and representing 3D objects and scenes. However, to establish a ubiquitous presence in everyday me…