A single unified multimodal model matches leading task-specialized vision systems across detection, segmentation, dense geometry, and multi-view 3D by casting all outputs as native text or image generation.
Geospecific View Generation Geometry-Context Aware High-Resolution Ground View Inference from Satellite Views , booktitle = ECCV, series =
5 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
5
Pith papers citing it
1
external citations · OpenAlex
years
2026 5representative citing papers
Text-guided class-agnostic counting models exhibit significant weaknesses in grounding textual prompts to visual objects, as demonstrated by new negative-label and distractor tests on a multi-category dataset.
SegRAG is a training-free retrieval-augmented framework that extracts class-specific point prompts from a filtered DINOv3 feature bank to boost SAM3 semantic segmentation performance on standard and agricultural benchmarks.
Sat3DGen improves geometric RMSE from 6.76m to 5.20m and FID from ~40 to 19 for street-level 3D generation from satellite images via geometry-centric constraints and perspective training.
The submitted paper simultaneously claims that oracle bounding-box cropping degrades medical VQA and that it improves it, with the abstract evaluating a different model set than the body.
citing papers explorer
-
Vision as Unified Multimodal Generation
A single unified multimodal model matches leading task-specialized vision systems across detection, segmentation, dense geometry, and multi-view 3D by casting all outputs as native text or image generation.
-
Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting
Text-guided class-agnostic counting models exhibit significant weaknesses in grounding textual prompts to visual objects, as demonstrated by new negative-label and distractor tests on a multi-category dataset.
-
SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation
SegRAG is a training-free retrieval-augmented framework that extracts class-specific point prompts from a filtered DINOv3 feature bank to boost SAM3 semantic segmentation performance on standard and agricultural benchmarks.
-
Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
Sat3DGen improves geometric RMSE from 6.76m to 5.20m and FID from ~40 to 19 for street-level 3D generation from satellite images via geometry-centric constraints and perspective training.
-
Why Does Grounding Hurt Medical VQA? Benchmarking, Diagnosis, and Fine-Tuning of Vision-Language Models
The submitted paper simultaneously claims that oracle bounding-box cropping degrades medical VQA and that it improves it, with the abstract evaluating a different model set than the body.