9 papers · 1 filter
GSta: Efficient Training Scheme with Siestaed Gaussians for Monocular 3D Scene Reconstruction
Anil Armagan, Albert Saà-Garriga, Bruno Manganelli +2
Gaussian Splatting (GS) is a popular approach for 3D reconstruction, mostly due to its ability to converge reasonably fast, faithfully represent the scene and render (novel) views…
Rethinking Encoder-Decoder Flow Through Shared Structures
Frederik Laboyrie, Mehmet Kerim Yucel, Albert Saa-Garriga
Dense prediction tasks have enjoyed a growing complexity of encoder architectures, decoders, however, have remained largely the same. They rely on individual blocks decoding interm…
Trick-GS: A Balanced Bag of Tricks for Efficient Gaussian Splatting
Anil Armagan, Albert Saà-Garriga, Bruno Manganelli +2
Gaussian splatting (GS) for 3D reconstruction has become quite popular due to their fast training, inference speeds and high quality reconstruction. However, GS-based reconstructio…
CheapNVS: Real-Time On-Device Narrow-Baseline Novel View Synthesis
Konstantinos Georgiadis, Mehmet Kerim Yucel, Albert Saa-Garriga
Single-view novel view synthesis (NVS) is a notorious problem due to its ill-posed nature, and often requires large, computationally expensive approaches to produce tangible result…
Finding Waldo: Towards Efficient Exploration of NeRF Scene Spaces
Evangelos Skartados, Mehmet Kerim Yucel, Bruno Manganelli +2
Neural Radiance Fields (NeRF) have quickly become the primary approach for 3D reconstruction and novel view synthesis in recent years due to their remarkable performance. Despite t…
TrickVOS: A Bag of Tricks for Video Object Segmentation
Evangelos Skartados, Konstantinos Georgiadis, Mehmet Kerim Yucel +5
Space-time memory (STM) network methods have been dominant in semi-supervised video object segmentation (SVOS) due to their remarkable performance. In this work, we identify three…