Research map / 3D vision / 3D generation
DeepVoxels: Learning Persistent 3D Feature Embeddings
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 a persistent 3D feature volume with geometric reprojection rather than a 2D image-to-image mapping | Novel view synthesis · Mean across Vase, Pedestal, Chair, and Cube | PSNR: 23.63 -> 30.55 | Helped |
| Add the occlusion module with softmax-weighted visibility along each ray (ablation) | DeepVoxels · Cube | PSNR: 23.26 -> 28.42 | Helped |
| Add the occlusion module with softmax-weighted visibility along each ray (ablation) | DeepVoxels · Pedestal | PSNR: 30.02 -> 32.35 | Helped |
Closest papers by meaning
- Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations (NeurIPS 2025 · similarity 0.87)
- DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization (ICLR 2024 · similarity 0.86)
- WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space (ICLR 2024 · similarity 0.86)
- Decompositional Neural Scene Reconstruction with Generative Diffusion Prior (CVPR 2025 · similarity 0.85)
- DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision (CVPR 2024 · similarity 0.85)
- DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features (NeurIPS 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.