NePO: Neural Point Octrees for Large‐Scale Novel View Synthesis
We introduce Neural Point Octrees (NePOs), a scalable radiance field representation that organises point clouds hierarchically for efficient optimisation and rendering of large scale scenes. NePOs enable level of detail selection, joint refinement of appearance and camera poses, and real‐time rendering of hundreds of millions of points.
Noah Lewis +3 more
wiley +1 more source
Real-Time Vision-Based Fall Detection Systems for the Elderly: A Systematic Review. [PDF]
Nabizade M +5 more
europepmc +1 more source
Democratising Multi‐Projector Displays
Spatially augmented reality (SAR) transforms large, surround, collaborative experiences out of VR/AR headsets to the real world by merging content from projectors with the physical environment. This detailed state‐of‐the‐art survey reports on the advancements in multi‐projector aggregation and hardware technologies used to achieve SAR and build ...
Aditi Majumder, Muhammad Twaha Ibrahim
wiley +1 more source
Recognition of Daily Activities Through Multi-Modal Deep Learning: A Video, Pose, and Object-Aware Approach for Ambient Assisted Living. [PDF]
Hashemifard K +2 more
europepmc +1 more source
MaX4Zero: Masked Extended Attention for Zero‐Shot Virtual Try‐On In The Wild
Max4Zero is a zero‐shot, training‐free virtual try‐on method that leverages diffusion priors and extended attention for accurate garment transfer. By warping reference garments and mitigating texture sticking, it achieves superior fidelity, garment preservation and identity consistency over state‐of‐the‐art methods without additional training ...
Nadav Orzech +4 more
wiley +1 more source
Feasibility and Operational Limits of a Minimum-Cost Indirect UAV Thermal Sensing Workflow Based on Smartphone-Displayed Infrared Video. [PDF]
Stoyanov Y +6 more
europepmc +1 more source
RotGS: Rotation‐Guided 3D Gaussian Splatting for Turntable Sequences without Structure‐from‐Motion
Abstract The field of 3D reconstruction from multi‐view images has advanced rapidly thanks to 3D Gaussian Splatting (3DGS), which enables efficient and photorealistic scene representation. However, optimizing 3DGS requires high‐quality images from various viewpoints with accurate camera poses.
Kyumin Kim +3 more
wiley +1 more source
Story2Board: A Training‐Free Approach for Expressive Visual Storytelling
Abstract We present Story2Board, a training‐free framework for expressive storyboard generation from natural language. Existing methods narrowly focus on subject identity, overlooking key aspects of visual storytelling such as spatial composition, background evolution, and narrative pacing.
D. Dinkevich +4 more
wiley +1 more source
A Method for Detecting Cattle Behaviors Based on RGB-Depth Dual-Modal Information Fusion. [PDF]
Chen Z, Xie J, Mao L, Chen Q, Wang L.
europepmc +1 more source
PBR‐Inspired Controllable Diffusion for Image Generation
Abstract Despite recent advances in text‐to‐image generation, controlling geometric layout and PBR material properties in synthesized scenes remains challenging. We present a pipeline that first produces a G‐buffer (albedo, normals, depth, roughness, shading, and metallic) from a text prompt and then renders a final image through a PBR‐inspired branch ...
Bowen Xue +3 more
wiley +1 more source

