Research map / 3D vision / Face and shape
Progressive Pose-Guided 4D Animal Reconstruction from Monocular Video
Siyuan Li, Weiying Chen, Yilin Wang, Xinxin Zuo, Xingyu Li, Li Cheng
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 part-conditioned deformation stage after pose refinement (ablation) | Ours · Artemis | PSNR: 22.796 -> 24.027 | Improved |
| add learnable part anchors (ablation) | Ours · Artemis | LPIPS: 0.086 -> 0.065 | Improved |
| initialize Gaussians from shape prior instead of random (ablation) | Ours · Artemis | PSNR: 23.891 -> 24.027 | Improved |
| use symmetry-aware temporal encoding (ablation) | Ours · Artemis | PSNR: 23.873 -> 24.027 | Improved |
| make skinning field learnable instead of fixed (ablation) | Ours · Artemis | PSNR: 23.934 -> 24.027 | Improved |
| use progressive pose-guided method vs D-3DGS* | Ours · Artemis | Chamfer distance / diag: 0.0181 -> 0.0156 | Improved |
| use Ours instead of DreamMesh4D on APTv2 | Ours · APTv2 input-view | PSNR: 26.000 -> 24.938 | Hurt |
| use Ours instead of D-3DGS* on DAVIS | Ours · DAVIS input-view | PSNR: 25.776 -> 26.321 | Improved |
| use Ours instead of GVFDiffusion on DAVIS | Ours · DAVIS novel-view | KID-16V: 0.145 -> 0.108 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- GART* — GART: Gaussian Articulated Template Models (CVPR 2024) · better on 6 of 6 shared results
- DreamMesh4D — DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation (NeurIPS 2024) · better on 0 of 3 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
- Web-Scale Collection of Video Data for 4D Animal Reconstruction (NeurIPS 2025 · similarity 0.90)
- BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting (NeurIPS 2026 · similarity 0.89)
- Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos (ECCV 2024 · similarity 0.89)
- WildDepth: A Multimodal Dataset for 3D Wildlife Perception and Depth Estimation (ECCV 2026 · similarity 0.89)
- SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild (NeurIPS 2026 · similarity 0.87)
- Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance (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.
