Research map / Detection and segmentation / CNN features
SemIE: Semantically-Aware Image Extrapolation
Bholeshwar Khurana, Soumya Ranjan Dash, Abhishek Bhatia, Aniruddha Mahapatra, Hrituraj Singh, Kuldeep Kulkarni
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add instance-aware context normalization (IaCN) (ablation) | SemIE without patch discriminator · Cityscapes | FID: 48.77 -> 47.76 | Improved |
| add patch co-occurrence discriminator (ablation) | SemIE without IaCN · Cityscapes | FID: 48.77 -> 48.72 | No clear effect |
| add patch co-occurrence discriminator to model with IaCN (ablation) | SemIE with IaCN · Cityscapes | FID: 47.76 -> 47.67 | No clear effect |
| add IaCN to model with patch discriminator (ablation) | SemIE with D_patch · Cityscapes | FID: 48.72 -> 47.67 | Improved |
| extrapolate in semantic label space with panoptic maps instead of the SPGNet++ pipeline | SPGNet++ · Cityscapes | FID: 52.14 -> 47.67 | Improved |
| extrapolate in semantic label space with panoptic maps instead of the SPGNet++ pipeline | SPGNet++ · ADE20K-bedroom | FID: 97.23 -> 90.45 | Improved |
| use a strong SPADE-based generator with multiscale discriminator for SPGNet | SPGNet · Cityscapes | FID: 83.84 -> 52.14 | Improved |
| use semantic-label-space extrapolation instead of RGB-space outpainting (Outpainting-SRN) | Outpainting-SRN · Cityscapes | FID: 66.89 -> 47.67 | Improved |
| add instance boundary channel supervision in semantic label extrapolation (ablation) | POGNet · Cityscapes and ADE20K-bedroom | shape realism (qualitative) | Improved |
| use single-stage SPADE extrapolation without label-space stages (ablation) | SemIE stage 4 only · Cityscapes | new-object generation (qualitative) | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SPGNet — SPGNet: Semantic Prediction Guidance for Scene Parsing (ICCV 2019) · better on 13 of 14 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Wide-Context Semantic Image Extrapolation (CVPR 2019 · similarity 0.88)
- UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation (TPAMI 2025 · similarity 0.86)
- Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation (IJCV 2023 · similarity 0.86)
- Segmenter: Transformer for Semantic Segmentation (ICCV 2021 · similarity 0.85)
- Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization (NeurIPS 2022 · similarity 0.84)
- A Generative Approach at the Instance-Level for Image Segmentation Under Limited Training Data Conditions (Student Abstract) (AAAI 2025 · similarity 0.84)
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.
