Research map / 3D vision / Face and shape
An Adversarial Neuro-Tensorial Approach for Learning Disentangled Representations
Mengjiao Wang, Zhixin Shu, Shiyang Cheng, Yannis Panagakis, Dimitris Samaras, Stefanos Zafeiriou
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 |
|---|---|---|---|
| use proposed tensor latent model instead of prior method 2 for normals | disentangling network · Photoface normal estimation | mean angular error (degrees): 30.09 -> 28.67 | Improved |
| use proposed model instead of prior method 2 | disentangling network · Photoface normal estimation | fraction within 35 degrees: 84.6 -> 89.1 | Improved |
| use proposed model instead of prior method 2 | disentangling network · Photoface normal estimation | fraction within 40 degrees: 98.1 -> 96.3 | Hurt |
| use proposed z_id instead of prior latent C for identity | disentangling network · Multi-PIE (frontal only) | identity accuracy: 19.18 -> 99.33 | Improved |
| use proposed z_exp instead of prior latent E for expression | disentangling network · Multi-PIE (frontal only) | expression accuracy: 35.49 -> 78.92 | Improved |
| use proposed z_ill instead of prior latent L for illumination | disentangling network · Multi-PIE (frontal only) | illumination accuracy: 48.85 -> 64.11 | Improved |
| use proposed disentangled Z_exp and Z_p instead of adversarial auto-encoder latent Z_0 | disentangling network · Multi-PIE t-SNE | cluster quality | Improved |
Closest papers by meaning
- Overcoming the Disentanglement vs Reconstruction Trade-off via Jacobian Supervision (ICLR 2019 · similarity 0.91)
- Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis (ICCV 2019 · similarity 0.90)
- An Image is Worth More Than a Thousand Words: Towards Disentanglement in The Wild (NeurIPS 2021 · similarity 0.89)
- Learning Disentangled Representations with Latent Variation Predictability (ECCV 2020 · similarity 0.89)
- InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs (TPAMI 2020 · similarity 0.89)
- Disentangled Representation Learning via Modular Compositional Bias (NeurIPS 2025 · similarity 0.87)
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.
