Research map / 3D vision / 3D generation
NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views
Read the paperCheck 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 NeuralLift-360 instead of DietNeRF | Single-image 3D lifting · Average across eight scenes | CLIP Distance: 0.5162 -> 0.4498 | Helped |
| Replace the depth ranking loss with L1 depth loss (ablation) | NeuralLift-360 · Single-image 3D lifting | visual quality | Hurt |
| Replace the CLIP-guided diffusion prior with CLIP (ablation) | NeuralLift-360 · Single-image 3D lifting | visual quality | Hurt |
| Use the pre-trained diffusion model without fine-tuning (ablation) | NeuralLift-360 · Single-image 3D lifting | reference consistency | Hurt |
| Remove CLIP guidance from the diffusion prior (ablation) | NeuralLift-360 · Single-image 3D lifting | reference similarity | Hurt |
Closest papers by meaning
- Diffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D (CVPR 2024 · similarity 0.86)
- Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D (CVPR 2024 · similarity 0.86)
- Denoising Diffusion via Image-Based Rendering (ICLR 2024 · similarity 0.86)
- MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views (NeurIPS 2024 · similarity 0.85)
- DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data (CVPR 2024 · similarity 0.85)
- Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors (ICLR 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.