Visual generation models are evolving from passive renderers to interactive agentic world modelers, but current systems lack spatial reasoning, temporal consistency, and causal understanding, with evaluations overemphasizing perceptual quality.
Shapesplat: A large-scale dataset of gaussian splats and their self-supervised pretraining.arXiv preprint arXiv:2408.10906, 2024b
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Comparative benchmark of geometric deep learning models on 3D Gaussian Splatting representations for scene classification via end-to-end training, linear probing, and clustering.
citing papers explorer
-
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Visual generation models are evolving from passive renderers to interactive agentic world modelers, but current systems lack spatial reasoning, temporal consistency, and causal understanding, with evaluations overemphasizing perceptual quality.
-
Learning Representations from 3D Gaussian Splats
Comparative benchmark of geometric deep learning models on 3D Gaussian Splatting representations for scene classification via end-to-end training, linear probing, and clustering.