Cheng Sun

16

Papers

88

Total Citations

Papers (16)

SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation

FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

Seg2Reg: Differentiable 2D Segmentation to 1D Regression Rendering for 360 Room Layout Reconstruction

HoHoNet: 360 Indoor Holistic Understanding With Latent Horizontal Features

Indoor Panorama Planar 3D Reconstruction via Divide and Conquer

Direct Voxel Grid Optimization: Super-Fast Convergence for Radiance Fields Reconstruction

Specialize and Fuse: Pyramidal Output Representation for Semantic Segmentation

Neural-PBIR Reconstruction of Shape, Material, and Illumination

Hashing Neural Video Decomposition with Multiplicative Residuals in Space-Time

ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection

Multiview Regenerative Morphing with Dual Flows

Data Efficient 3D Learner via Knowledge Transferred from 2D Model

Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering

Segment Anything, Even Occluded

HorizonNet: Learning Room Layout With 1D Representation and Pano Stretch Data Augmentation