Research map / Image generation / Text-to-image diffusion
Subjective Camera 1.0: Bridging Human Cognition and Visual Reconstruction through Sequence-Aware Sketch-Guided Diffusion
Haoyang Chen, Dongfang Sun, Caoyuan Ma, Shiqin Wang, Kewei Zhang, Zheng Wang, Zhixiang Wang
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 sequence-aware sketch-guided method instead of FreeControl | Subjective Camera · CMC | FID: 14.52 -> 11.56 | Improved |
| use sequence-aware method instead of FreeControl | Subjective Camera · FMC | FID: 11.17 -> 10.18 | Improved |
| use sequence-aware method instead of Multi-Sketch | Subjective Camera · FMC | CLIP-T: 72.02 -> 74.25 | Improved |
| use sequence-aware method instead of ControlNet | Subjective Camera · CMC | CLIP-T: 61.71 -> 66.64 | Improved |
| use sequence-aware method instead of PNP | Subjective Camera · FMC | CLIP-I: 0.593 -> 0.797 | Improved |
| use sequence-aware method instead of PNP | Subjective Camera · CMC | HPS: 0.840 -> 0.850 | Improved |
| add Concept-wise Sequential Optimization over overall-perception single-step sketch guidance (ablation) | Subjective Camera · FMC and CMC | qualitative layout alignment | Improved |
| add Sketch Encoding module (ablation) | Subjective Camera · FMC and CMC | qualitative geometric alignment | Improved |
| add sketch guidance to T2I baseline (OP) (ablation) | T2I diffusion · FMC and CMC | qualitative concept positioning | Mixed |
| compare to text-reward optimization on image quality (user study Q2) | Subjective Camera · user study | Q2 visual quality | Hurt |
| shorten reference image viewing time to 5s (ablation) | Subjective Camera · user study vs FreeControl | preference | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- FreeControl — FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition (CVPR 2024) · better on 7 of 7 shared results
- ControlNet — ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback (ECCV 2024) · better on 7 of 7 shared results
- T2I-Adapter — T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion Models (AAAI 2024) · better on 3 of 3 shared results
- Uni-ControlNet — Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models (NeurIPS 2023) · better on 2 of 2 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
- ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models (CVPR 2024 · similarity 0.87)
- It's All About Your Sketch: Democratising Sketch Control in Diffusion Models (CVPR 2024 · similarity 0.86)
- DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis (CVPR 2024 · similarity 0.86)
- Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search (NeurIPS 2025 · similarity 0.86)
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos (NeurIPS 2025 · similarity 0.86)
- FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation (CVPR 2024 · 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.
