9 papers
AnyGS2Mesh: Feed-Forward Mesh Reconstruction from 3D Gaussian Splatting with Arbitrary-Resolution Views
Yuxuan Song, Fan Gao, Yibo Zhao +3
Existing 3D mesh reconstruction methods from Gaussian scene representations predominantly rely on iterative optimization, resulting in slow inference and limited scalability to hig…
LightBridge: Feed-Forward Generative Relighting for 3D Gaussian Splatting
Hezhi Cao, Panhao Cheng, huangsheng du +3
3D Gaussian Splatting (3DGS) achieves high-quality, real-time novel view synthesis, but the resulting assets have baked-in illumination and cannot be easily relit. Inverse renderin…
CORGI: Consistency-Aware 3D Dog Reconstruction from a Single Image in the Wild
Yuxiao Wu, Weile Li, Boyi Zhu +3
Reconstructing high-fidelity 3D models of highly articulated animals, such as dogs, from a single in-the-wild image remains a formidable challenge. In this paper, we introduce CORG…
Mesh2GS: White-Box 3DGS Construction via Plenoptic Sampling
Haoran Zhu, Youcheng Cai, Huangsheng Du +2
3D Gaussian Splatting (3DGS) has emerged as a promising method for high-quality, real-time 3D reconstruction. To associate 3DGS with mesh representations, existing methods primaril…
RenderFormer++: Scalable and Physics-Informed Feed-Forward Neural Rendering
Huangsheng Du, Haoran Zhu, Youcheng Cai +2
We present RenderFormer++, a scalable and physics-informed feed-forward neural rendering framework for global illumination in mesh scenes. Existing Transformer-based neural renderi…
3DGS: Joint Super Sampling and Frame Interpolation for Real-Time Large-Scale 3DGS Rendering
Yibo Zhao, Fan Gao, Youcheng Cai +1
3D Gaussian Splatting (3DGS) enables high-quality real-time 3D rendering but faces challenges in efficiently scaling to ultra-dense scenes and high-resolution due to computational…
STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction
Runze Wang, Yuxuan Song, Youcheng Cai +1
Online 3D reconstruction from streaming inputs requires both long-term temporal consistency and efficient memory usage. Although causal variants of VGGT address this challenge thro…
FrameNeRF: A Simple and Efficient Framework for Few-shot Novel View Synthesis
Yan Xing, Pan Wang, Ligang Liu +2
We present a novel framework, called FrameNeRF, designed to apply off-the-shelf fast high-fidelity NeRF models with fast training speed and high rendering quality for few-shot nove…
High-Quality Real-Time Rendering Using Subpixel Sampling Reconstruction
Boyu Zhang, Hongliang Yuan, Mingyan Zhu +2
Generating high-quality, realistic rendering images for real-time applications generally requires tracing a few samples-per-pixel (spp) and using deep learning-based approaches to…