Part²GS introduces a part-aware 3D Gaussian representation with physics-guided motion constraints and a repel point field for high-fidelity modeling of articulated objects.
Nerf: Representing scenes as neural radiance fields for view synthesis.Communications of the ACM
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 4roles
background 1polarities
background 1representative citing papers
Learned 2D data association and uncertainty—not recurrent architectures—drive the performance gains of deep visual SLAM, as shown by integrating them into classical ORB-SLAM3.
Adding per-frame camera-pose supervision to a video MLLM improves spatial and general video question answering by 2–6% and yields SOTA streaming pose estimates on ScanNet.
LingBot-World is presented as an open-source world model that delivers high-fidelity simulation, minute-level contextual consistency, and real-time interactivity under one second latency.
citing papers explorer
-
Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting
Part²GS introduces a part-aware 3D Gaussian representation with physics-guided motion constraints and a repel point field for high-fidelity modeling of articulated objects.
-
Why does Deep Learning Improve Visual SLAM?
Learned 2D data association and uncertainty—not recurrent architectures—drive the performance gains of deep visual SLAM, as shown by integrating them into classical ORB-SLAM3.
-
Cambrian-P: Pose-Grounded Video Understanding
Adding per-frame camera-pose supervision to a video MLLM improves spatial and general video question answering by 2–6% and yields SOTA streaming pose estimates on ScanNet.
-
Advancing Open-source World Models
LingBot-World is presented as an open-source world model that delivers high-fidelity simulation, minute-level contextual consistency, and real-time interactivity under one second latency.