Research map / Detection and segmentation / Open-set and few-shot detection
Generative Modeling of Infinite Occluded Objects for Compositional Scene Representation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| explicit occlusion modeling (ρ-based forefront-object compositing) vs. N-EM/AIR | proposed model · Occluded datasets (Table 1) | AMI (%) | Helped |
| explicit occlusion modeling | proposed model · Occluded datasets, OOA adjusted order (Table 2) | OOA (%) | Helped |
| proposed model vs AIR on occluded Gray-M/RGB2-M/RGB3-M-type data | proposed model · Occluded datasets (Table 1) | AMI (%) | Mixed |
| proposed model generalization to 4-object test scenes (K=4) | proposed model · Generalization with occlusion (Table 3) | OCA (%) | Mixed |
| N-EM replaced by mixture-based pixel segregation with entangled representations | N-EM baseline · Occluded datasets (Table 1) | AMI (%) | Hurt |
Closest papers by meaning
- Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints (AAAI 2022 · similarity 0.91)
- Compositional Scene Understanding through Inverse Generative Modeling (ICML 2025 · similarity 0.90)
- COAT: Measuring Object Compositionality in Emergent Representations (ICML 2022 · similarity 0.89)
- GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations (ICLR 2020 · similarity 0.89)
- Compositional Transformers for Scene Generation (NeurIPS 2021 · similarity 0.88)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.