Research map / Image generation / GANs
RoboCoDraw: Robotic Avatar Drawing with GAN-Based Style Transfer and Time-Efficient Path Optimization
Tianying Wang, Wei Qi Toh, Hao Zhang, Xiuchao Sui, Shaohua Li, Yong Liu, Wei Jing
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 a facial-area translation stream to the whole-image CycleGAN | AvatarGAN · Real facial area cycle consistency | mean cycle consistency loss: 0.2620 -> 0.0329 | Improved |
| Add a facial-area translation stream to the whole-image CycleGAN | AvatarGAN · Avatar facial area cycle consistency | mean cycle consistency loss: 0.3298 -> 0.0252 | Improved |
| Add a facial-area translation stream to the whole-image CycleGAN | AvatarGAN · Face cycle consistency | mean cycle consistency loss: 0.0355 -> 0.0367 | Hurt |
| Add a facial-area translation stream to the whole-image CycleGAN | AvatarGAN · Avatar cycle consistency | mean cycle consistency loss: 0.0167 -> 0.0252 | Hurt |
| Add 2-opt and LK local improvement to RKGA (ablation) | robot drawing path optimization · Path optimization, G1-G5 average | path fitness improvement over greedy (%): 16.8 -> 17.3 | Improved |
| Add LK local improvement to greedy search with 2-opt | robot drawing path optimization · Path optimization, G1-G5 average | path fitness improvement over greedy (%): 12.1 -> 15.1 | Improved |
| Use RKGA rather than greedy search, retaining 2-opt | robot drawing path optimization · Path optimization, G1-G5 average | path fitness improvement over greedy (%): 12.1 -> 16.8 | Improved |
Closest papers by meaning
- SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines (AAAI 2023 · similarity 0.84)
- AvatarVerse: High-Quality & Stable 3D Avatar Creation from Text and Pose (AAAI 2024 · similarity 0.82)
- AvatarArtist: Open-Domain 4D Avatarization (CVPR 2025 · similarity 0.82)
- AirSketch: Generative Motion to Sketch (NeurIPS 2024 · similarity 0.82)
- LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example (CVPR 2024 · similarity 0.82)
- AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation (ICLR 2025 · similarity 0.82)
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.
