Research map / 3D vision / Gaussian splatting
FLAG-4D: Flow-Guided Local-Global Dual-Deformation Model for 4D Reconstruction
Guan Yuan Tan, Ngoc Tuan Vu, Arghya Pal, Sailaja Rajanala, Raphael C W Phan, Mettu Srinivas, Chee-Ming Ting
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 Instantaneous Deformation Network (local deformation) alongside GMN (ablation) | FLAG-4D · NeRF-DS | PSNR: 24.01 -> 24.23 | Improved |
| add Global Motion Network with optical flow guidance alongside IDN (ablation) | FLAG-4D · NeRF-DS | PSNR: 23.39 -> 24.23 | Improved |
| add mutual learning between IDN and GMN (ablation) | FLAG-4D · NeRF-DS | PSNR: 23.70 -> 24.23 | Improved |
| add mutual learning between IDN and GMN (ablation) | FLAG-4D · NeRF-DS | LPIPS: 0.157 -> 0.157 | No clear effect |
| FLAG-4D versus best prior methods on HyperNeRF vrig | FLAG-4D · HyperNeRF vrig | PSNR / SSIM: PSNR 22.33 vs D-MiSo 22.47; SSIM 0.78 vs 0.61 | Mixed |
| FLAG-4D versus D-MiSo on NeRF-DS | FLAG-4D · NeRF-DS | LPIPS: 0.198 vs 0.151 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.
- D-MiSo — D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup (NeurIPS 2024) · better on 2 of 4 shared results
- SC-GS — SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes (CVPR 2024) · better on 2 of 2 shared results
- MotionGS — MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting (NeurIPS 2024) · better on 1 of 1 shared result
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
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.89)
- Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle (CVPR 2024 · similarity 0.88)
- 4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time (NeurIPS 2025 · similarity 0.88)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.87)
- Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking (CVPR 2024 · similarity 0.87)
- Flux4D: Flow-based Unsupervised 4D Reconstruction (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.
