Search Results for author:
Found 10 papers, 0 papers with code
Modeling Ambient Scene Dynamics for Free-view Synthesis
We introduce a novel method for dynamic free-view synthesis of an ambient scenes from a monocular capture bringing a immersive quality to the viewing experience.
LTM: Lightweight Textured Mesh Extraction and Refinement of Large Unbounded Scenes for Efficient Storage and Real-time Rendering
We validate the effectiveness of the proposed method on large unbounded scenes from mip-NeRF 360 Tanks & Temples and Deep Blending datasets achieving at-par rendering quality with 73x reduced triangles and 11x reduction in memory footprint.
FusedRF: Fusing Multiple Radiance Fields
The fused RF has the same render times and memory utilizations as a single RF.
Long-term Visual Map Sparsification with Heterogeneous GNN
We address the problem of map sparsification for long-term visual localization.
Analysis and Mitigations of Reverse Engineering Attacks on Local Feature Descriptors
This poses a potential risk to user privacy.
View-graph Selection Framework for SfM
Accuracy and efficiency of large-scale SfM is crucially dependent on the input view-graph.
A Unified View-Graph Selection Framework for Structure from Motion
Accuracy and efficiency of large-scale SfM is crucially dependent on the input view-graph.
Learning to Hash-tag Videos with Tag2Vec
In this paper, we study the problem of generating relevant and useful hash-tags for short video clips.
From Traditional to Modern : Domain Adaptation for Action Classification in Short Social Video Clips
In this paper, we focus on the problem of unsupervised action classification in wild vines using traditional labeled datasets.
Multistage SFM: A Coarse-to-Fine Approach for 3D Reconstruction
We present a multistage approach for SFM reconstruction of a single component that breaks the sequential nature of the incremental SFM methods.
