Stars
[CVPR 2023 Highlight] Neural Kernel Surface Reconstruction
[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies
[CVPR 2024] 4K4D: Real-Time 4D View Synthesis at 4K Resolution
FlashMLA: Efficient MLA Decoding Kernel for Hopper GPUs
Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation
Open Overleaf/ShareLaTex projects in vscode, with full collaboration support.
[CVPR'24] Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors
TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.
手把手带你实战 Huggingface Transformers 课程视频同步更新在B站与YouTube
Single Image to 3D using Cross-Domain Diffusion for 3D Generation
[ICLR 2025] Official implementation of "DiffSplat: Repurposing Image Diffusion Models for Scalable 3D Gaussian Splat Generation".
[CVPR 2024] DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior
Stable Video Diffusion Training Code and Extensions.
[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)
🌟A curated list of DUSt3R-related papers and resources, tracking recent advancements using this geometric foundation model.
[ICLR 2025] Latent Radiance Fields with 3D-aware 2D Representations
[CVPR'24] DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization
ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
[CVPR 2025] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
official code of Efficient Depth-Guided Urban View Synthesis
Original reference implementation of "EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis"
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.
[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.