Research map / Image generation / Image restoration
Jointly Aligning Millions of Images With Deep Penalised Reconstruction Congealing
Roberto Annunziata, Christos Sagonas, Jacques Cali
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 penalised low-capacity auto-encoder loss C to the reference-based similarity loss D (ablation) | Proposed congealing on MNIST · MNIST (6000 images per digit) | variance of aligned images (qualitative) | Improved |
| add similarity loss D with reference image to C-only objective (ablation) | Proposed congealing on MNIST · MNIST (6000 images per digit) | alignment quality (qualitative) | Improved |
| use proposed method instead of RASL on enlarged initial bounding box (+30%) | LFW Jennifer_Capriati · LFW landmark error | landmark error: 6.77% -> 1.92% | Improved |
| coarser initialisation (+15% bounding box) for the proposed method | Proposed on LFW George_W_Bush · LFW landmark error | landmark error: 2.67% -> 3.84% | Hurt |
| coarser initialisation (+30% bounding box) for RASL | RASL on LFW George_W_Bush · LFW landmark error | landmark error: 2.88% -> 6.29% | Hurt |
| coarser initialisation (+30% bounding box) for the proposed method | Proposed on LFW Tony_Blair · LFW landmark error | landmark error: 2.39% -> 2.55% | Mixed |
| use Deep Congealing instead of proposed method with original initialisation | LFW George_W_Bush · LFW landmark error | landmark error: 2.67% -> 3.97% | Hurt |
Closest papers by meaning
- Dense Cross-Scale Image Alignment with Fully Spatial Correlation and Just Noticeable Difference Guidance (AAAI 2026 · similarity 0.89)
- SpaceJAM: a Lightweight and Regularization-free Method for Fast Joint Alignment of Images (ECCV 2024 · similarity 0.88)
- Auto-Regressive Transformation for Image Alignment (ICCV 2025 · similarity 0.88)
- FastJAM: a Fast Joint Alignment Model for Images (NeurIPS 2025 · similarity 0.87)
- Faster Than Real-Time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses (ICCV 2017 · similarity 0.87)
- IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder (NeurIPS 2026 · similarity 0.85)
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.
