SeMo3D: Unifying 3D Generation, Editing, and Completion via Selective Modeling
cs.CV
Submitted: 2026-11-02
Updated: 2026-11-02
Project page: https://xiaokunsun.github.io/SeMo3D.github.io
Terminology
Sources
- Qwen3-VL Technical Report
- EditP23: 3D Editing via Propagation of Image Prompts to Multi-View
- Demystifying MMD GANs
- Native 3D Editing with Full Attention
- Text-Image Conditioned 3D Generation
- Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models
- SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling
- LLMs Meet Multimodal Generation and Editing: A Survey
- Classifier-Free Diffusion Guidance
- Axolotl3D: a Unified Framework for Faithful 3D Shape Completion
- Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
- Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets
- Pixal3D: Pixel-Aligned 3D Generation from Images
- VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
- Advances in 3D Generation: A Survey
- Flow Matching for Generative Modeling
- A Comprehensive Survey on 3D Content Generation
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
- Feedforward 3D Editing via Text-Steerable Image-to-3D
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs