Unverified50% confidenceFactExact time
Panoptic scene graph generation (PSG) is an extended variant of the scene graph generation (SGG) task, whose goal is to model all objects in an image and the pairwise relations between them as a graph structure, using panoptic segmentation masks as object representations and outputting a set of triples (subject, predicate, object).
1
Sources
50%
Confidence
Long-term
Relevance
11/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe PSGAgent framework includes a Visual Highlight Tool that filters irrelevant contextual noise through relation-oriented segmentation, focusing the model on foreground objects and relations relevant to the current reasoning.70% similarUnverified矢量化是指将位图图像(如JPG、PNG)转换为矢量图形(如SVG、EPS)的过程64% similarUnverifiedSGE-Goal is a spatially grounded decomposed editing framework that splits target image synthesis into two steps: first predicting the initial and final 2D edit region masks, then generating the target image based on the masks.63% similarUnverifiedEmbedded bitmaps are the most common invisible minefield in vector submissions: many design tools, when exporting SVG, bake effects that cannot be vectorized into PNG or JPEG and stuff them into the SVG via the <image> tag.63% similarUnverifiedGeoState contains three key components: a scene tokenizer, a geometry decoder and an autoregressive world model; the scene tokenizer aggregates multi-view GFM features into a viewpoint-decoupled scene state; the geometry decoder queries the scene state with camera rays to render observations from a specific viewpoint; the autoregressive world model performs prediction in the decoupled scene state space and models camera motion independently.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1141777API
curl https://kongchang.com/api/v1/knowledge/claims/1141777MCP
get_claim(id=1141777)