Research map / Video / Video generation
Plenoptic Video Generation
Xiao Fu, Shitao Tang, Min Shi, Xian Liu, Jinwei Gu, Ming-Yu Liu, Dahua Lin, Chen-Hsuan Lin
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 progressive context-size training (ablation) | PlenopticDreamer · Basic benchmark | TransErr: 0.63 -> 0.54 | Improved |
| add progressive context-size training (ablation) | PlenopticDreamer · Basic benchmark | FVD: 453.8 -> 425.8 | Improved |
| add self-conditioned training (ablation) | PlenopticDreamer · Basic benchmark | FVD: 464.3 -> 425.8 | Improved |
| add self-conditioned training (ablation) | PlenopticDreamer · Basic benchmark | IQ: 56.7 -> 58.5 | Improved |
| add FOV-based context retrieval instead of random retrieval (ablation) | PlenopticDreamer · Basic benchmark | Mat. Pix. (K), 12 shots: 32.4 -> 41.2 | Improved |
| add FOV-based context retrieval instead of random retrieval (ablation) | PlenopticDreamer · Basic benchmark | FVD: 520.5 -> 425.8 | Improved |
| increase retrieved context videos from 4 to 6 (ablation) | PlenopticDreamer · Basic benchmark, 6 shots | Mat. Pix. (K): 51.2 -> 52.1 | Mixed |
| increase retrieved context videos from 6 to 10 (ablation) | PlenopticDreamer · Basic benchmark, 12 shots | Mat. Pix. (K): 43.6 -> 40.8 | Hurt |
| increase in-context videos k from 2 to 4 (ablation) | PlenopticDreamer · Basic benchmark, 12 shots | Mat. Pix. (K): 40.8 -> 41.2 | Improved |
| increase in-context videos k from 4 to 6 (ablation) | PlenopticDreamer · Basic benchmark, 12 shots | Mat. Pix. (K): 41.2 -> 40.4 | Hurt |
| use 4-shot instead of 1-shot synthetic videos for self-conditioning (ablation) | PlenopticDreamer · Basic benchmark | FVD: 425.8 -> 460.2 | Hurt |
| replace ReCamMaster* with PlenopticDreamer | ReCamMaster* · Agibot benchmark | PSNR: 13.84 -> 14.54 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ReCamMaster — ReCamMaster: Camera-Controlled Generative Rendering from A Single Video (ICCV 2025) · better on 7 of 7 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
- SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints (ICLR 2025 · similarity 0.88)
- MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences (ICLR 2025 · similarity 0.86)
- WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception (NeurIPS 2025 · similarity 0.86)
- DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos (NeurIPS 2024 · similarity 0.86)
- Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation (NeurIPS 2026 · similarity 0.85)
- VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control (ICLR 2025 · 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.
