A framework and dataset that constructs seasonal 3D mountain landscapes from over 85,000 sparse webcam images across 32 locations and 13 timestamps by mesh projection and conditional diffusion inpainting, enabling standard relighting.
arXiv preprint arXiv:2403.09637 (2024)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
ClickSeg3D uses a point Transformer encoder and hierarchical mask decoder with semantic embeddings to enable single-pass multi-object 3D interactive segmentation from sparse points, reporting over 20% mIoU gains versus baselines and 8-10% cross-dataset improvements with one click per instance.
Chorus pretrains a shared 3D Gaussian scene encoder via multi-teacher distillation to capture holistic features from high-level semantics to fine-grained structure, with strong transfer on segmentation and point-cloud tasks using far fewer scenes.
Forecast-GS predicts task-completed 3D states via Gaussian splatting to achieve higher success rates than baselines in real-world language-conditioned manipulation tasks.
citing papers explorer
-
SeasonScapes: Learning Large-scale Re-lightable 3D Landscapes with Seasonal Variation from Sparse Webcams
A framework and dataset that constructs seasonal 3D mountain landscapes from over 85,000 sparse webcam images across 32 locations and 13 timestamps by mesh projection and conditional diffusion inpainting, enabling standard relighting.
-
ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings
ClickSeg3D uses a point Transformer encoder and hierarchical mask decoder with semantic embeddings to enable single-pass multi-object 3D interactive segmentation from sparse points, reporting over 20% mIoU gains versus baselines and 8-10% cross-dataset improvements with one click per instance.
-
Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding
Chorus pretrains a shared 3D Gaussian scene encoder via multi-teacher distillation to capture holistic features from high-level semantics to fine-grained structure, with strong transfer on segmentation and point-cloud tasks using far fewer scenes.
-
Forecast-aware Gaussian Splatting for Predictive 3D Representation in Language-Guided Pick-and-Place Manipulation
Forecast-GS predicts task-completed 3D states via Gaussian splatting to achieve higher success rates than baselines in real-world language-conditioned manipulation tasks.