-
Shanghai Jiao Tong University
- Shanghai, China
-
17:51
(UTC -12:00) - https://scholar.google.com.hk/citations?user=5kW5apkAAAAJ&hl=zh-CN
Lists (1)
Sort Name ascending (A-Z)
Stars
[NIPS 2025] MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation
Data Preprocess of DTC-MultiLight Dataset. (Blend Rendering and Gaussian Optimizing)
ARTDECO unifies 3D foundation priors with structured scene representations, enabling robust and generalizable 3D reconstruction of diverse real-world scenes using only monocular video.
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
[SIGGRAPH 2025 Conference Paper] Virtualized 3D Gaussians (V3DG)
[NeurIPS 2025] InternScenes: A Large-scale Interactive Indoor Scene Dataset with Realistic Layouts.
[SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
[TIP-2025] Official Pytorch implementation of "Structural Similarity-Inspired Unfolding for Lightweight Image Super-Resolution"
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
[CVPR2025 Highlight]: Implicit Correspondence Learning for Image-to-Point Cloud Registration
Lets make video diffusion practical!
Fast mesh to 3D gaussian splat conversion
[CVPR 2025] Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes
[ICCV 2025] Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
Original reference implementation of "EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis"
ControlLoRA Version 3: LoRA Is All You Need to Control the Spatial Information of Stable Diffusion.
Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation
Code for ICCV'2025 "Real3D: Scaling Up Large Reconstruction Models with Real-World Images"
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
[NeurIPS 2024] Geometry-Aware Large Reconstruction Model for Efficient and High-Quality 3D Generation
Official code for NeurIPS 2024 paper LRM-Zero: Training Large Reconstruction Models with Synthesized Data
An open-source impl. of Large Reconstruction Models
cskrren / gsplat-2dgs
Forked from FantasticOven2/gsplatCUDA accelerated rasterization of gaussian splatting
[ ECCV 2024 ] MotionLCM: This repo is the official implementation of "MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model"
InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds
Official implementation of the SIGGRAPH 2024 paper "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets"