Research map / Image generation / Text-to-image diffusion
Not All Birds Look The Same: Identity-Preserving Generation For Birds
Aaron Sun, Oindrila Saha, Subhransu Maji
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 |
|---|---|---|---|
| fine-tune on same-class NABirds pairs as proxy identity | OminiControl FLUX-Schnell (Fill) · NABLA | DINO similarity: 0.41 -> 0.57 | Improved |
| fine-tune on proxy identity pairs | OminiControl FLUX-Schnell (Fill) · NABLA | MSE: 77.1 -> 54.7 | Improved |
| fine-tune on proxy identity pairs | Insert Anything · NABLA | MSE: 62.9 -> 55.0 | Improved |
| fine-tune on proxy identity pairs | OminiControl FLUX-Schnell (Depth) · iNat-Unseen | DINO similarity: 0.55 -> 0.61 | Improved |
| use FLUX-Kontext backbone instead of FLUX-Schnell (ablation) | OminiControl (Fill) · NABLA | DINO similarity: 0.57 -> 0.78 | Improved |
| use inpainting (Fill) control instead of depth control (ablation) | OminiControl FLUX-Kontext · NABLA | MSE: 57.0 -> 51.0 | Improved |
| use keypoint control instead of Fill control (ablation) | OminiControl FLUX-Kontext · NABLA | MSE: 51.0 -> 66.7 | Hurt |
| combine depth and fill controls (ablation) | OminiControl · NABLA | identity metrics | No clear effect |
Closest papers by meaning
- Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife (NeurIPS 2026 · similarity 0.89)
- RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs (CVPR 2026 · similarity 0.89)
- BirdCollect: A Comprehensive Benchmark for Analyzing Dense Bird Flock Attributes (AAAI 2024 · similarity 0.85)
- CleverBirds: A Multiple-Choice Benchmark for Fine-grained Human Knowledge Tracing (NeurIPS 2025 · similarity 0.85)
- Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis (CVPR 2025 · similarity 0.84)
- Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition (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.
