hanlinm2 / projective-geometry
[CVPR 2024] Shadows Don’t Lie and Lines Can’t Bend! Generative Models don’t know Projective Geometry...for now
☆26Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for projective-geometry
- ☆38Updated 11 months ago
- [CVPR 2024] G3DR: Generative 3D Reconstruction in ImageNet☆27Updated 4 months ago
- Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation (D-SDS) | NeurIPS 2023☆42Updated 9 months ago
- Sora Generates Videos with Stunning Geometrical Consistency☆47Updated 7 months ago
- ☆22Updated 6 months ago
- RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Models☆89Updated last year
- Poison-splat: Computation Cost Attack on 3D Gaussian Splatting☆34Updated last month
- Code for paper Background Prompting for Improved Object Depth☆29Updated last year
- ☆32Updated last month
- "Taming Mode Collapse in Score Distillation for Text-to-3D Generation" by Peihao Wang, Dejia Xu, Zhiwen Fan, Dilin Wang, Sreyas Mohan, Fo…☆48Updated 9 months ago
- Scene-Conditional 3D Object Stylization and Composition☆31Updated 11 months ago
- Implementation of Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding☆23Updated 2 weeks ago
- Official implementation of Aurora☆81Updated last year
- [ECCV 2024] HiFi-123: Towards High-fidelity One Image to 3D Content Generation☆59Updated 4 months ago
- ☆15Updated 7 months ago
- Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics☆55Updated last month
- ☆40Updated 3 years ago
- Official code for ICCV2023 paper: Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis☆28Updated 10 months ago
- DreamGaussian with 2D-GS☆11Updated last month
- Unofficial Implementation of "Stable Video Diffusion Multi-View"☆73Updated 7 months ago
- ☆52Updated last month
- [ECCV 2024 Oral] ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction☆44Updated 3 months ago
- (CVPR 2024) NViST: In the wild New View Synthesis from a Single Image with Transformers☆33Updated last month
- [CVPR2024] Official Codes for "Adversarial Score Distillation: When score distillation meets GAN"☆31Updated last month
- [NeurIPS 2024] MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing☆76Updated last week
- Official code repository for the paper: "TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision"☆40Updated last year
- [NeurIPS 2022 Spotlight] Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator☆30Updated 2 years ago
- Unsupervised Semantic Correspondence Using Stable Diffusion☆55Updated 11 months ago
- Official implementation of "Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive" (ICLR 2024)☆52Updated 2 months ago
- Evaluating Multiview Object Correspondence between Humans and Image models☆17Updated 2 months ago